diff --git a/normalization/blazepose_mapping.py b/normalization/blazepose_mapping.py
index 666aba7..ad24b55 100644
--- a/normalization/blazepose_mapping.py
+++ b/normalization/blazepose_mapping.py
@@ -61,20 +61,25 @@ def map_blazepose_keypoint(column):
     return f"{mapped}_{hand}{suffix}"
 
 
-def map_blazepose_df(df):
+def map_blazepose_df(df, rename=True):
+    to_drop = []
+    if rename:
+        renamings = {}
+        for column in df.columns:
+            mapped_column = map_blazepose_keypoint(column)
+            if mapped_column:
+                renamings[column] = mapped_column
+            else:
+                to_drop.append(column)
+        df = df.rename(columns=renamings)
+
     for index, row in df.iterrows():
 
+        sequence_size = len(row["leftEar_Y"])
         lsx = row["leftShoulder_X"]
         rsx = row["rightShoulder_X"]
         lsy = row["leftShoulder_Y"]
         rsy = row["rightShoulder_Y"]
-        # convert all to list
-        lsx = lsx[1:-1].split(",")
-        rsx = rsx[1:-1].split(",")
-        lsy = lsy[1:-1].split(",")
-        rsy = rsy[1:-1].split(",")
-        sequence_size = len(lsx)
-
         neck_x = []
         neck_y = []
         # Treat each element of the sequence (analyzed frame) individually
@@ -84,4 +89,5 @@ def map_blazepose_df(df):
         df.loc[index, "neck_X"] = str(neck_x)
         df.loc[index, "neck_Y"] = str(neck_y)
 
-    return df
+    df.drop(columns=to_drop, inplace=True)
+    return df
\ No newline at end of file
diff --git a/normalization/main.py b/normalization/main.py
index 9f4231f..2ed4891 100644
--- a/normalization/main.py
+++ b/normalization/main.py
@@ -5,30 +5,30 @@ import pandas as pd
 from normalization.hand_normalization import normalize_hands_full
 from normalization.body_normalization import normalize_body_full
 
-DATASET_PATH = './data/wlasl'
+DATASET_PATH = './data/processed'
 # Load the dataset
-df = pd.read_csv(os.path.join(DATASET_PATH, "WLASL100_train.csv"), encoding="utf-8")
+df = pd.read_csv(os.path.join(DATASET_PATH, "spoter_train.csv"), encoding="utf-8")
 
 print(df.head())
 print(df.columns)
 
 # Retrieve metadata
-video_size_heights = df["video_height"].to_list()
-video_size_widths = df["video_width"].to_list()
+# video_size_heights = df["video_height"].to_list()
+# video_size_widths = df["video_width"].to_list()
 
 # Delete redundant (non-related) properties
-del df["video_height"]
-del df["video_width"]
+# del df["video_height"]
+# del df["video_width"]
 
 # Temporarily remove other relevant metadata
 labels = df["labels"].to_list()
-video_fps = df["fps"].to_list()
+signs = df["sign"].to_list()
+
 del df["labels"]
-del df["fps"]
-del df["split"]
-del df["video_id"]
-del df["label_name"]
-del df["length"]
+del df["sign"]
+del df["path"]
+del df["participant_id"]
+del df["sequence_id"]
 
 # Convert the strings into lists
 
@@ -41,7 +41,7 @@ for column in df.columns:
 
 # Perform the normalizations
 df = normalize_hands_full(df)
-df, invalid_row_indexes = normalize_body_full(df)
+# df, invalid_row_indexes = normalize_body_full(df)
 
 # Clear lists of items from deleted rows
 # labels = [t for i, t in enumerate(labels) if i not in invalid_row_indexes]
@@ -49,6 +49,6 @@ df, invalid_row_indexes = normalize_body_full(df)
 
 # Return the metadata back to the dataset
 df["labels"] = labels
-df["fps"] = video_fps
+df["sign"] = signs
 
-df.to_csv(os.path.join(DATASET_PATH, "wlasl_train_norm.csv"), encoding="utf-8", index=False)
+df.to_csv(os.path.join(DATASET_PATH, "spoter_train_norm.csv"), encoding="utf-8", index=False)
diff --git a/notebooks/visualize_embeddings.ipynb b/notebooks/visualize_embeddings.ipynb
index 4268c5a..3ad8c09 100644
--- a/notebooks/visualize_embeddings.ipynb
+++ b/notebooks/visualize_embeddings.ipynb
@@ -2,10 +2,19 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 22,
    "id": "8ef5cd92",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The autoreload extension is already loaded. To reload it, use:\n",
+      "  %reload_ext autoreload\n"
+     ]
+    }
+   ],
    "source": [
     "%load_ext autoreload\n",
     "%autoreload 2"
@@ -13,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 23,
    "id": "78c4643a",
    "metadata": {},
    "outputs": [],
@@ -28,7 +37,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 24,
    "id": "ffba4333",
    "metadata": {},
    "outputs": [],
@@ -38,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 25,
    "id": "5bc81f71",
    "metadata": {},
    "outputs": [],
@@ -48,7 +57,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 49,
    "id": "3de8bcf2",
    "metadata": {
     "lines_to_next_cell": 0
@@ -64,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 50,
    "id": "91a045ba",
    "metadata": {},
    "outputs": [],
@@ -84,17 +93,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 51,
    "id": "bc50c296",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<torch._C.Generator at 0x7fe4a6429f50>"
+       "<torch._C.Generator at 0x7fc6eb911fd0>"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 51,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -115,7 +124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 52,
    "id": "82766a17",
    "metadata": {},
    "outputs": [],
@@ -129,7 +138,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 62,
    "id": "ead15a36",
    "metadata": {},
    "outputs": [
@@ -139,7 +148,7 @@
        "<All keys matched successfully>"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 62,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -151,7 +160,7 @@
     "# checkpoint = torch.load(model.get_weights())\n",
     "\n",
     "\n",
-    "CHECKPOINT_PATH = \"../out-checkpoints/augment_rotate_75_x8/checkpoint_embed_18.pth\"\n",
+    "CHECKPOINT_PATH = \"../out-checkpoints/augment_rotate_75_x8/checkpoint_embed_187.pth\"\n",
     "checkpoint = torch.load(CHECKPOINT_PATH, map_location=device)\n",
     "\n",
     "\n",
@@ -166,7 +175,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 71,
    "id": "20f8036d",
    "metadata": {},
    "outputs": [],
@@ -185,7 +194,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 72,
    "id": "758716b6",
    "metadata": {},
    "outputs": [],
@@ -205,7 +214,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 73,
    "id": "f1527959",
    "metadata": {},
    "outputs": [
@@ -222,7 +231,7 @@
    ],
    "source": [
     "dataloaders = {}\n",
-    "splits = ['train', 'val']\n",
+    "splits = ['test']\n",
     "dfs = {}\n",
     "for split in splits:\n",
     "    split_set_path = op.join(dataset_folder, split_dataset_path.format(split))\n",
@@ -255,7 +264,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 74,
    "id": "3c3af5bf",
    "metadata": {
     "lines_to_next_cell": 0
@@ -264,10 +273,10 @@
     {
      "data": {
       "text/plain": [
-       "1220"
+       "2000"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 74,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -286,13 +295,13 @@
     "    #     df['video_fn'] = df['video_id'].apply(lambda video_id: os.path.join(BASE_DATA_FOLDER, f'lsa/videos/{video_id}.mp4'))\n",
     "    dfs[split] = df\n",
     "\n",
-    "df = pd.concat([dfs['train'].sample(20), dfs['val']]).reset_index(drop=True)\n",
+    "df = pd.concat([dfs['test']]).reset_index(drop=True)\n",
     "len(df)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 75,
    "id": "dccbe1b9",
    "metadata": {},
    "outputs": [],
@@ -315,7 +324,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 76,
    "id": "904298f0",
    "metadata": {},
    "outputs": [],
@@ -329,7 +338,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 77,
    "id": "42832f7c",
    "metadata": {
     "scrolled": false
@@ -340,7 +349,7 @@
       "text/html": [
        "<div class=\"bk-root\">\n",
        "        <a href=\"https://bokeh.org\" target=\"_blank\" class=\"bk-logo bk-logo-small bk-logo-notebook\"></a>\n",
-       "        <span id=\"1144\">Loading BokehJS ...</span>\n",
+       "        <span id=\"1849\">Loading BokehJS ...</span>\n",
        "    </div>\n"
       ]
      },
@@ -349,7 +358,7 @@
     },
     {
      "data": {
-      "application/javascript": "(function(root) {\n  function now() {\n    return new Date();\n  }\n\n  const force = true;\n\n  if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n    root._bokeh_onload_callbacks = [];\n    root._bokeh_is_loading = undefined;\n  }\n\nconst JS_MIME_TYPE = 'application/javascript';\n  const HTML_MIME_TYPE = 'text/html';\n  const EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n  const CLASS_NAME = 'output_bokeh rendered_html';\n\n  /**\n   * Render data to the DOM node\n   */\n  function render(props, node) {\n    const script = document.createElement(\"script\");\n    node.appendChild(script);\n  }\n\n  /**\n   * Handle when an output is cleared or removed\n   */\n  function handleClearOutput(event, handle) {\n    const cell = handle.cell;\n\n    const id = cell.output_area._bokeh_element_id;\n    const server_id = cell.output_area._bokeh_server_id;\n    // Clean up Bokeh references\n    if (id != null && id in Bokeh.index) {\n      Bokeh.index[id].model.document.clear();\n      delete Bokeh.index[id];\n    }\n\n    if (server_id !== undefined) {\n      // Clean up Bokeh references\n      const cmd_clean = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n      cell.notebook.kernel.execute(cmd_clean, {\n        iopub: {\n          output: function(msg) {\n            const id = msg.content.text.trim();\n            if (id in Bokeh.index) {\n              Bokeh.index[id].model.document.clear();\n              delete Bokeh.index[id];\n            }\n          }\n        }\n      });\n      // Destroy server and session\n      const cmd_destroy = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n      cell.notebook.kernel.execute(cmd_destroy);\n    }\n  }\n\n  /**\n   * Handle when a new output is added\n   */\n  function handleAddOutput(event, handle) {\n    const output_area = handle.output_area;\n    const output = handle.output;\n\n    // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n    if ((output.output_type != \"display_data\") || (!Object.prototype.hasOwnProperty.call(output.data, EXEC_MIME_TYPE))) {\n      return\n    }\n\n    const toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n\n    if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n      toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n      // store reference to embed id on output_area\n      output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n    }\n    if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n      const bk_div = document.createElement(\"div\");\n      bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n      const script_attrs = bk_div.children[0].attributes;\n      for (let i = 0; i < script_attrs.length; i++) {\n        toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n        toinsert[toinsert.length - 1].firstChild.textContent = bk_div.children[0].textContent\n      }\n      // store reference to server id on output_area\n      output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n    }\n  }\n\n  function register_renderer(events, OutputArea) {\n\n    function append_mime(data, metadata, element) {\n      // create a DOM node to render to\n      const toinsert = this.create_output_subarea(\n        metadata,\n        CLASS_NAME,\n        EXEC_MIME_TYPE\n      );\n      this.keyboard_manager.register_events(toinsert);\n      // Render to node\n      const props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n      render(props, toinsert[toinsert.length - 1]);\n      element.append(toinsert);\n      return toinsert\n    }\n\n    /* Handle when an output is cleared or removed */\n    events.on('clear_output.CodeCell', handleClearOutput);\n    events.on('delete.Cell', handleClearOutput);\n\n    /* Handle when a new output is added */\n    events.on('output_added.OutputArea', handleAddOutput);\n\n    /**\n     * Register the mime type and append_mime function with output_area\n     */\n    OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n      /* Is output safe? */\n      safe: true,\n      /* Index of renderer in `output_area.display_order` */\n      index: 0\n    });\n  }\n\n  // register the mime type if in Jupyter Notebook environment and previously unregistered\n  if (root.Jupyter !== undefined) {\n    const events = require('base/js/events');\n    const OutputArea = require('notebook/js/outputarea').OutputArea;\n\n    if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n      register_renderer(events, OutputArea);\n    }\n  }\n  if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n    root._bokeh_timeout = Date.now() + 5000;\n    root._bokeh_failed_load = false;\n  }\n\n  const NB_LOAD_WARNING = {'data': {'text/html':\n     \"<div style='background-color: #fdd'>\\n\"+\n     \"<p>\\n\"+\n     \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n     \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n     \"</p>\\n\"+\n     \"<ul>\\n\"+\n     \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n     \"<li>use INLINE resources instead, as so:</li>\\n\"+\n     \"</ul>\\n\"+\n     \"<code>\\n\"+\n     \"from bokeh.resources import INLINE\\n\"+\n     \"output_notebook(resources=INLINE)\\n\"+\n     \"</code>\\n\"+\n     \"</div>\"}};\n\n  function display_loaded() {\n    const el = document.getElementById(\"1144\");\n    if (el != null) {\n      el.textContent = \"BokehJS is loading...\";\n    }\n    if (root.Bokeh !== undefined) {\n      if (el != null) {\n        el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n      }\n    } else if (Date.now() < root._bokeh_timeout) {\n      setTimeout(display_loaded, 100)\n    }\n  }\n\n  function run_callbacks() {\n    try {\n      root._bokeh_onload_callbacks.forEach(function(callback) {\n        if (callback != null)\n          callback();\n      });\n    } finally {\n      delete root._bokeh_onload_callbacks\n    }\n    console.debug(\"Bokeh: all callbacks have finished\");\n  }\n\n  function load_libs(css_urls, js_urls, callback) {\n    if (css_urls == null) css_urls = [];\n    if (js_urls == null) js_urls = [];\n\n    root._bokeh_onload_callbacks.push(callback);\n    if (root._bokeh_is_loading > 0) {\n      console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n      return null;\n    }\n    if (js_urls == null || js_urls.length === 0) {\n      run_callbacks();\n      return null;\n    }\n    console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n    root._bokeh_is_loading = css_urls.length + js_urls.length;\n\n    function on_load() {\n      root._bokeh_is_loading--;\n      if (root._bokeh_is_loading === 0) {\n        console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n        run_callbacks()\n      }\n    }\n\n    function on_error(url) {\n      console.error(\"failed to load \" + url);\n    }\n\n    for (let i = 0; i < css_urls.length; i++) {\n      const url = css_urls[i];\n      const element = document.createElement(\"link\");\n      element.onload = on_load;\n      element.onerror = on_error.bind(null, url);\n      element.rel = \"stylesheet\";\n      element.type = \"text/css\";\n      element.href = url;\n      console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n      document.body.appendChild(element);\n    }\n\n    for (let i = 0; i < js_urls.length; i++) {\n      const url = js_urls[i];\n      const element = document.createElement('script');\n      element.onload = on_load;\n      element.onerror = on_error.bind(null, url);\n      element.async = false;\n      element.src = url;\n      console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n      document.head.appendChild(element);\n    }\n  };\n\n  function inject_raw_css(css) {\n    const element = document.createElement(\"style\");\n    element.appendChild(document.createTextNode(css));\n    document.body.appendChild(element);\n  }\n\n  const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-2.4.3.min.js\"];\n  const css_urls = [];\n\n  const inline_js = [    function(Bokeh) {\n      Bokeh.set_log_level(\"info\");\n    },\nfunction(Bokeh) {\n    }\n  ];\n\n  function run_inline_js() {\n    if (root.Bokeh !== undefined || force === true) {\n          for (let i = 0; i < inline_js.length; i++) {\n      inline_js[i].call(root, root.Bokeh);\n    }\nif (force === true) {\n        display_loaded();\n      }} else if (Date.now() < root._bokeh_timeout) {\n      setTimeout(run_inline_js, 100);\n    } else if (!root._bokeh_failed_load) {\n      console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n      root._bokeh_failed_load = true;\n    } else if (force !== true) {\n      const cell = $(document.getElementById(\"1144\")).parents('.cell').data().cell;\n      cell.output_area.append_execute_result(NB_LOAD_WARNING)\n    }\n  }\n\n  if (root._bokeh_is_loading === 0) {\n    console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n    run_inline_js();\n  } else {\n    load_libs(css_urls, js_urls, function() {\n      console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n      run_inline_js();\n    });\n  }\n}(window));",
+      "application/javascript": "(function(root) {\n  function now() {\n    return new Date();\n  }\n\n  const force = true;\n\n  if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n    root._bokeh_onload_callbacks = [];\n    root._bokeh_is_loading = undefined;\n  }\n\nconst JS_MIME_TYPE = 'application/javascript';\n  const HTML_MIME_TYPE = 'text/html';\n  const EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n  const CLASS_NAME = 'output_bokeh rendered_html';\n\n  /**\n   * Render data to the DOM node\n   */\n  function render(props, node) {\n    const script = document.createElement(\"script\");\n    node.appendChild(script);\n  }\n\n  /**\n   * Handle when an output is cleared or removed\n   */\n  function handleClearOutput(event, handle) {\n    const cell = handle.cell;\n\n    const id = cell.output_area._bokeh_element_id;\n    const server_id = cell.output_area._bokeh_server_id;\n    // Clean up Bokeh references\n    if (id != null && id in Bokeh.index) {\n      Bokeh.index[id].model.document.clear();\n      delete Bokeh.index[id];\n    }\n\n    if (server_id !== undefined) {\n      // Clean up Bokeh references\n      const cmd_clean = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n      cell.notebook.kernel.execute(cmd_clean, {\n        iopub: {\n          output: function(msg) {\n            const id = msg.content.text.trim();\n            if (id in Bokeh.index) {\n              Bokeh.index[id].model.document.clear();\n              delete Bokeh.index[id];\n            }\n          }\n        }\n      });\n      // Destroy server and session\n      const cmd_destroy = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n      cell.notebook.kernel.execute(cmd_destroy);\n    }\n  }\n\n  /**\n   * Handle when a new output is added\n   */\n  function handleAddOutput(event, handle) {\n    const output_area = handle.output_area;\n    const output = handle.output;\n\n    // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n    if ((output.output_type != \"display_data\") || (!Object.prototype.hasOwnProperty.call(output.data, EXEC_MIME_TYPE))) {\n      return\n    }\n\n    const toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n\n    if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n      toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n      // store reference to embed id on output_area\n      output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n    }\n    if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n      const bk_div = document.createElement(\"div\");\n      bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n      const script_attrs = bk_div.children[0].attributes;\n      for (let i = 0; i < script_attrs.length; i++) {\n        toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n        toinsert[toinsert.length - 1].firstChild.textContent = bk_div.children[0].textContent\n      }\n      // store reference to server id on output_area\n      output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n    }\n  }\n\n  function register_renderer(events, OutputArea) {\n\n    function append_mime(data, metadata, element) {\n      // create a DOM node to render to\n      const toinsert = this.create_output_subarea(\n        metadata,\n        CLASS_NAME,\n        EXEC_MIME_TYPE\n      );\n      this.keyboard_manager.register_events(toinsert);\n      // Render to node\n      const props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n      render(props, toinsert[toinsert.length - 1]);\n      element.append(toinsert);\n      return toinsert\n    }\n\n    /* Handle when an output is cleared or removed */\n    events.on('clear_output.CodeCell', handleClearOutput);\n    events.on('delete.Cell', handleClearOutput);\n\n    /* Handle when a new output is added */\n    events.on('output_added.OutputArea', handleAddOutput);\n\n    /**\n     * Register the mime type and append_mime function with output_area\n     */\n    OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n      /* Is output safe? */\n      safe: true,\n      /* Index of renderer in `output_area.display_order` */\n      index: 0\n    });\n  }\n\n  // register the mime type if in Jupyter Notebook environment and previously unregistered\n  if (root.Jupyter !== undefined) {\n    const events = require('base/js/events');\n    const OutputArea = require('notebook/js/outputarea').OutputArea;\n\n    if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n      register_renderer(events, OutputArea);\n    }\n  }\n  if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n    root._bokeh_timeout = Date.now() + 5000;\n    root._bokeh_failed_load = false;\n  }\n\n  const NB_LOAD_WARNING = {'data': {'text/html':\n     \"<div style='background-color: #fdd'>\\n\"+\n     \"<p>\\n\"+\n     \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n     \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n     \"</p>\\n\"+\n     \"<ul>\\n\"+\n     \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n     \"<li>use INLINE resources instead, as so:</li>\\n\"+\n     \"</ul>\\n\"+\n     \"<code>\\n\"+\n     \"from bokeh.resources import INLINE\\n\"+\n     \"output_notebook(resources=INLINE)\\n\"+\n     \"</code>\\n\"+\n     \"</div>\"}};\n\n  function display_loaded() {\n    const el = document.getElementById(\"1849\");\n    if (el != null) {\n      el.textContent = \"BokehJS is loading...\";\n    }\n    if (root.Bokeh !== undefined) {\n      if (el != null) {\n        el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n      }\n    } else if (Date.now() < root._bokeh_timeout) {\n      setTimeout(display_loaded, 100)\n    }\n  }\n\n  function run_callbacks() {\n    try {\n      root._bokeh_onload_callbacks.forEach(function(callback) {\n        if (callback != null)\n          callback();\n      });\n    } finally {\n      delete root._bokeh_onload_callbacks\n    }\n    console.debug(\"Bokeh: all callbacks have finished\");\n  }\n\n  function load_libs(css_urls, js_urls, callback) {\n    if (css_urls == null) css_urls = [];\n    if (js_urls == null) js_urls = [];\n\n    root._bokeh_onload_callbacks.push(callback);\n    if (root._bokeh_is_loading > 0) {\n      console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n      return null;\n    }\n    if (js_urls == null || js_urls.length === 0) {\n      run_callbacks();\n      return null;\n    }\n    console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n    root._bokeh_is_loading = css_urls.length + js_urls.length;\n\n    function on_load() {\n      root._bokeh_is_loading--;\n      if (root._bokeh_is_loading === 0) {\n        console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n        run_callbacks()\n      }\n    }\n\n    function on_error(url) {\n      console.error(\"failed to load \" + url);\n    }\n\n    for (let i = 0; i < css_urls.length; i++) {\n      const url = css_urls[i];\n      const element = document.createElement(\"link\");\n      element.onload = on_load;\n      element.onerror = on_error.bind(null, url);\n      element.rel = \"stylesheet\";\n      element.type = \"text/css\";\n      element.href = url;\n      console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n      document.body.appendChild(element);\n    }\n\n    for (let i = 0; i < js_urls.length; i++) {\n      const url = js_urls[i];\n      const element = document.createElement('script');\n      element.onload = on_load;\n      element.onerror = on_error.bind(null, url);\n      element.async = false;\n      element.src = url;\n      console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n      document.head.appendChild(element);\n    }\n  };\n\n  function inject_raw_css(css) {\n    const element = document.createElement(\"style\");\n    element.appendChild(document.createTextNode(css));\n    document.body.appendChild(element);\n  }\n\n  const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-2.4.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-2.4.3.min.js\"];\n  const css_urls = [];\n\n  const inline_js = [    function(Bokeh) {\n      Bokeh.set_log_level(\"info\");\n    },\nfunction(Bokeh) {\n    }\n  ];\n\n  function run_inline_js() {\n    if (root.Bokeh !== undefined || force === true) {\n          for (let i = 0; i < inline_js.length; i++) {\n      inline_js[i].call(root, root.Bokeh);\n    }\nif (force === true) {\n        display_loaded();\n      }} else if (Date.now() < root._bokeh_timeout) {\n      setTimeout(run_inline_js, 100);\n    } else if (!root._bokeh_failed_load) {\n      console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n      root._bokeh_failed_load = true;\n    } else if (force !== true) {\n      const cell = $(document.getElementById(\"1849\")).parents('.cell').data().cell;\n      cell.output_area.append_execute_result(NB_LOAD_WARNING)\n    }\n  }\n\n  if (root._bokeh_is_loading === 0) {\n    console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n    run_inline_js();\n  } else {\n    load_libs(css_urls, js_urls, function() {\n      console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n      run_inline_js();\n    });\n  }\n}(window));",
       "application/vnd.bokehjs_load.v0+json": ""
      },
      "metadata": {},
@@ -373,7 +382,10 @@
     "        </div>\n",
     "    </div>\n",
     "\"\"\"\n",
-    "cmap = LinearColorMapper(palette=\"Turbo256\", low=0, high=len(set_labels))\n",
+    "\n",
+    "# get labels\n",
+    "labels = df['sign'].values\n",
+    "cmap = LinearColorMapper(palette=\"Turbo256\", low=0, high=len(labels))\n",
     "\n",
     "output_notebook()\n",
     "# or \n",
@@ -387,7 +399,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 82,
    "id": "ead4daf7",
    "metadata": {
     "scrolled": false
@@ -395,23 +407,14 @@
    "outputs": [
     {
      "ename": "KeyError",
-     "evalue": "'label_name'",
+     "evalue": "21",
      "output_type": "error",
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "File \u001b[0;32m/usr/local/lib/python3.8/dist-packages/pandas/core/indexes/base.py:3802\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3801\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m-> 3802\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_engine\u001b[39m.\u001b[39;49mget_loc(casted_key)\n\u001b[1;32m   3803\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyError\u001b[39;00m \u001b[39mas\u001b[39;00m err:\n",
-      "File \u001b[0;32m/usr/local/lib/python3.8/dist-packages/pandas/_libs/index.pyx:138\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
-      "File \u001b[0;32m/usr/local/lib/python3.8/dist-packages/pandas/_libs/index.pyx:165\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
-      "File \u001b[0;32mpandas/_libs/hashtable_class_helper.pxi:5745\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
-      "File \u001b[0;32mpandas/_libs/hashtable_class_helper.pxi:5753\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
-      "\u001b[0;31mKeyError\u001b[0m: 'label_name'",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[29], line 5\u001b[0m\n\u001b[1;32m      1\u001b[0m column_data \u001b[39m=\u001b[39m \u001b[39mdict\u001b[39m(\n\u001b[1;32m      2\u001b[0m     x\u001b[39m=\u001b[39mdf[\u001b[39m'\u001b[39m\u001b[39mtsne_x\u001b[39m\u001b[39m'\u001b[39m],\n\u001b[1;32m      3\u001b[0m     y\u001b[39m=\u001b[39mdf[\u001b[39m'\u001b[39m\u001b[39mtsne_y\u001b[39m\u001b[39m'\u001b[39m],\n\u001b[1;32m      4\u001b[0m     label\u001b[39m=\u001b[39mdf[\u001b[39m'\u001b[39m\u001b[39msign\u001b[39m\u001b[39m'\u001b[39m],\n\u001b[0;32m----> 5\u001b[0m     label_desc\u001b[39m=\u001b[39mdf[\u001b[39m'\u001b[39;49m\u001b[39mlabel_name\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[1;32m      6\u001b[0m     split\u001b[39m=\u001b[39mdf[\u001b[39m'\u001b[39m\u001b[39msplit\u001b[39m\u001b[39m'\u001b[39m],\n\u001b[1;32m      7\u001b[0m     video_id\u001b[39m=\u001b[39mdf[\u001b[39m'\u001b[39m\u001b[39mvideo_id\u001b[39m\u001b[39m'\u001b[39m]\n\u001b[1;32m      8\u001b[0m )\n\u001b[1;32m     10\u001b[0m \u001b[39mif\u001b[39;00m use_img_div:\n\u001b[1;32m     11\u001b[0m     emb_videos \u001b[39m=\u001b[39m load_videos(df[\u001b[39m'\u001b[39m\u001b[39mvideo_fn\u001b[39m\u001b[39m'\u001b[39m])\n",
-      "File \u001b[0;32m/usr/local/lib/python3.8/dist-packages/pandas/core/frame.py:3807\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   3805\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcolumns\u001b[39m.\u001b[39mnlevels \u001b[39m>\u001b[39m \u001b[39m1\u001b[39m:\n\u001b[1;32m   3806\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_getitem_multilevel(key)\n\u001b[0;32m-> 3807\u001b[0m indexer \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mcolumns\u001b[39m.\u001b[39;49mget_loc(key)\n\u001b[1;32m   3808\u001b[0m \u001b[39mif\u001b[39;00m is_integer(indexer):\n\u001b[1;32m   3809\u001b[0m     indexer \u001b[39m=\u001b[39m [indexer]\n",
-      "File \u001b[0;32m/usr/local/lib/python3.8/dist-packages/pandas/core/indexes/base.py:3804\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3802\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_engine\u001b[39m.\u001b[39mget_loc(casted_key)\n\u001b[1;32m   3803\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyError\u001b[39;00m \u001b[39mas\u001b[39;00m err:\n\u001b[0;32m-> 3804\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mKeyError\u001b[39;00m(key) \u001b[39mfrom\u001b[39;00m \u001b[39merr\u001b[39;00m\n\u001b[1;32m   3805\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mTypeError\u001b[39;00m:\n\u001b[1;32m   3806\u001b[0m     \u001b[39m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[1;32m   3807\u001b[0m     \u001b[39m#  InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[1;32m   3808\u001b[0m     \u001b[39m#  the TypeError.\u001b[39;00m\n\u001b[1;32m   3809\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_check_indexing_error(key)\n",
-      "\u001b[0;31mKeyError\u001b[0m: 'label_name'"
+      "Cell \u001b[0;32mIn[82], line 12\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[39m# map labels to 0 to num_classes\u001b[39;00m\n\u001b[1;32m     11\u001b[0m label_to_id \u001b[39m=\u001b[39m {label: i \u001b[39mfor\u001b[39;00m i, label \u001b[39min\u001b[39;00m \u001b[39menumerate\u001b[39m(set_labels)}\n\u001b[0;32m---> 12\u001b[0m column_data[\u001b[39m'\u001b[39m\u001b[39mlabels\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m [label_to_id[label] \u001b[39mfor\u001b[39;00m label \u001b[39min\u001b[39;00m column_data[\u001b[39m'\u001b[39m\u001b[39mlabel\u001b[39m\u001b[39m'\u001b[39m]]\n\u001b[1;32m     15\u001b[0m \u001b[39mif\u001b[39;00m use_img_div:\n\u001b[1;32m     16\u001b[0m     emb_videos \u001b[39m=\u001b[39m load_videos(df[\u001b[39m'\u001b[39m\u001b[39mvideo_fn\u001b[39m\u001b[39m'\u001b[39m])\n",
+      "Cell \u001b[0;32mIn[82], line 12\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[39m# map labels to 0 to num_classes\u001b[39;00m\n\u001b[1;32m     11\u001b[0m label_to_id \u001b[39m=\u001b[39m {label: i \u001b[39mfor\u001b[39;00m i, label \u001b[39min\u001b[39;00m \u001b[39menumerate\u001b[39m(set_labels)}\n\u001b[0;32m---> 12\u001b[0m column_data[\u001b[39m'\u001b[39m\u001b[39mlabels\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m [label_to_id[label] \u001b[39mfor\u001b[39;00m label \u001b[39min\u001b[39;00m column_data[\u001b[39m'\u001b[39m\u001b[39mlabel\u001b[39m\u001b[39m'\u001b[39m]]\n\u001b[1;32m     15\u001b[0m \u001b[39mif\u001b[39;00m use_img_div:\n\u001b[1;32m     16\u001b[0m     emb_videos \u001b[39m=\u001b[39m load_videos(df[\u001b[39m'\u001b[39m\u001b[39mvideo_fn\u001b[39m\u001b[39m'\u001b[39m])\n",
+      "\u001b[0;31mKeyError\u001b[0m: 21"
      ]
     }
    ],
@@ -422,22 +425,31 @@
     "    label=df['labels'],\n",
     "    label_desc=df['sign'],\n",
     "    split=df['split'],\n",
-    "    video_id=df['video_id']\n",
+    "    # video_id=df['video_id']\n",
     ")\n",
     "\n",
+    "# get unique labels\n",
+    "set_labels = list(set(labels))\n",
+    "\n",
+    "# map labels to 0 to num_classes\n",
+    "label_to_id = {label: i for i, label in enumerate(set_labels)}\n",
+    "column_data['labels'] = [label_to_id[label] for label in column_data['label']]\n",
+    "\n",
+    "\n",
     "if use_img_div:\n",
     "    emb_videos = load_videos(df['video_fn'])\n",
     "    column_data[\"videos\"] = emb_videos\n",
     "source = ColumnDataSource(data=column_data)\n",
     "\n",
-    "p.scatter('x', 'y',\n",
-    "     size=10,\n",
-    "     source=source,\n",
-    "     fill_color={\"field\": 'label', \"transform\": cmap},\n",
-    "     line_color={\"field\": 'label', \"transform\": cmap},         \n",
-    "     #legend_label={\"field\": 'split', \"transform\": lambda x: df['split']},\n",
-    "#      marker={\"field\": 'split'}\n",
-    "         )\n",
+    "# scatter plot with for each label another color\n",
+    "p.scatter(x='x',\n",
+    "            y='y',\n",
+    "            source=source,\n",
+    "            color={'field': 'label', 'transform': cmap},\n",
+    "            legend_field='label_desc',\n",
+    "            size=10,\n",
+    "            alpha=0.5)\n",
+    "\n",
     "\n",
     "show(p)"
    ]
diff --git a/preprocessing.py b/preprocessing.py
index 34ac917..ac4b7f5 100644
--- a/preprocessing.py
+++ b/preprocessing.py
@@ -1,5 +1,5 @@
 from argparse import ArgumentParser
-from preprocessing.create_wlasl_landmarks_dataset import parse_create_args, create
+from preprocessing.create_fingerspelling_dataset import parse_create_args, create
 from preprocessing.extract_mediapipe_landmarks import parse_extract_args, extract
 
 
diff --git a/preprocessing/create_fingerspelling_dataset.py b/preprocessing/create_fingerspelling_dataset.py
new file mode 100644
index 0000000..36ac643
--- /dev/null
+++ b/preprocessing/create_fingerspelling_dataset.py
@@ -0,0 +1,172 @@
+import os
+import os.path as op
+import json
+import shutil
+
+import cv2
+import mediapipe as mp
+import numpy as np
+import pandas as pd
+from utils import get_logger
+from tqdm.auto import tqdm
+from sklearn.model_selection import train_test_split
+from normalization.blazepose_mapping import map_blazepose_df
+
+BASE_DATA_FOLDER = 'data/'
+
+mp_drawing = mp.solutions.drawing_utils
+mp_drawing_styles = mp.solutions.drawing_styles
+mp_hands = mp.solutions.hands
+mp_holistic = mp.solutions.holistic
+pose_landmarks = mp_holistic.PoseLandmark
+hand_landmarks = mp_holistic.HandLandmark
+
+
+def get_landmarks_names():
+    '''
+    Returns landmark names for mediapipe holistic model
+    '''
+    pose_lmks = ','.join([f'{lmk.name.lower()}_x,{lmk.name.lower()}_y' for lmk in pose_landmarks])
+    left_hand_lmks = ','.join([f'left_hand_{lmk.name.lower()}_x,left_hand_{lmk.name.lower()}_y'
+                               for lmk in hand_landmarks])
+    right_hand_lmks = ','.join([f'right_hand_{lmk.name.lower()}_x,right_hand_{lmk.name.lower()}_y'
+                                for lmk in hand_landmarks])
+    lmks_names = f'{pose_lmks},{left_hand_lmks},{right_hand_lmks}'
+    return lmks_names
+
+
+def convert_to_str(arr, precision=6):
+    if isinstance(arr, np.ndarray):
+        values = []
+        for val in arr:
+            if val == 0:
+                values.append('0')
+            else:
+                values.append(f'{val:.{precision}f}')
+        return f"[{','.join(values)}]"
+    else:
+        return str(arr)
+
+
+def parse_create_args(parser):
+    parser.add_argument('--landmarks-dataset', '-lmks', required=True,
+                        help='Path to folder with landmarks npy files. \
+                            You need to run `extract_mediapipe_landmarks.py` script first')
+    parser.add_argument('--dataset-folder', '-df', default='data/wlasl',
+                        help='Path to folder where original `WLASL_v0.3.json` and `id_to_label.json` are stored. \
+                            Note that final CSV files will be saved in this folder too.')
+    parser.add_argument('--videos-folder', '-videos', default=None,
+                        help='Path to folder with videos. If None, then no information of videos (fps, length, \
+                            width and height) will be stored in final csv file')
+    parser.add_argument('--num-classes', '-nc', default=100, type=int, help='Number of classes to use in WLASL dataset')
+    parser.add_argument('--create-new-split', action='store_true')
+    parser.add_argument('--test-size', '-ts', default=0.25, type=float,
+                        help='Test split percentage size. Only required if --create-new-split is set')
+
+
+# python3 preprocessing.py --landmarks-dataset=data/landmarks -videos data/wlasl/videos
+def create(args):
+    logger = get_logger(__name__)
+
+    landmarks_dataset = args.landmarks_dataset
+    videos_folder = args.videos_folder
+    dataset_folder = args.dataset_folder
+    num_classes = args.num_classes
+    test_size = args.test_size
+
+    os.makedirs(dataset_folder, exist_ok=True)
+
+    # shutil.copy(os.path.join(BASE_DATA_FOLDER, 'wlasl/id_to_label.json'), dataset_folder)
+    # shutil.copy(os.path.join(BASE_DATA_FOLDER, 'wlasl/WLASL_v0.3.json'), dataset_folder)
+
+    # get files in landmarks_dataset folder
+    landmarks_files = os.listdir(landmarks_dataset)
+
+    video_data = []
+    for i, file in enumerate(tqdm(landmarks_files)):
+
+        # split by !
+        label = file.split('!')[0]
+        subset = file.split('!')[1].split('.')[0]
+        
+        # remove npy and set mp4
+        video_id = file.replace('.npy', "")
+
+
+        video_dict = {'video_id': video_id,
+                        'label_name': label,
+                        'split': subset}
+        
+        if videos_folder is not None:
+            cap = cv2.VideoCapture(op.join(videos_folder, f'{video_id}.mp4'))
+            if not cap.isOpened():
+                logger.warning(f'Video {video_id}.mp4 not found')
+                continue
+            width = cap.get(cv2.CAP_PROP_FRAME_WIDTH)
+            height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
+            fps = cap.get(cv2.CAP_PROP_FPS)
+            length = cap.get(cv2.CAP_PROP_FRAME_COUNT) / float(cap.get(cv2.CAP_PROP_FPS))
+            video_info = {'video_width': width,
+                            'video_height': height,
+                            'fps': fps,
+                            'length': length}
+            video_dict.update(video_info)
+        video_data.append(video_dict)
+
+    df_video = pd.DataFrame(video_data)
+    video_ids = df_video['video_id'].unique()
+    lmks_data = []
+    lmks_names = get_landmarks_names().split(',')
+
+    # get labels from df_video
+    labels = df_video['label_name'].unique()
+    # map labels to ids
+    label_to_id = {label: i for i, label in enumerate(labels)}
+
+    # add label_id column to df_video
+    df_video['labels'] = df_video['label_name'].map(label_to_id)
+
+    # export to json file as id to label
+    id_to_label = {i: label for label, i in label_to_id.items()}
+    with open(op.join(dataset_folder, 'id_to_label.json'), 'w') as f:
+        json.dump(id_to_label, f, indent=4)
+
+    for video_id in video_ids:
+        lmk_fn = op.join(landmarks_dataset, f'{video_id}.npy')
+        if not op.exists(lmk_fn):
+            logger.warning(f'{lmk_fn} file not found. Skipping')
+            continue
+        lmk = np.load(lmk_fn).T
+        lmks_dict = {'video_id': video_id}
+        for lmk_, name in zip(lmk, lmks_names):
+            lmks_dict[name] = lmk_
+        lmks_data.append(lmks_dict)
+
+    df_lmks = pd.DataFrame(lmks_data)
+    print(df_lmks)
+    df = pd.merge(df_video, df_lmks)
+    print(df)
+    aux_columns = ['split', 'video_id', 'labels', 'label_name']
+    if videos_folder is not None:
+        aux_columns += ['video_width', 'video_height', 'fps', 'length']
+    df_aux = df[aux_columns]
+    df = map_blazepose_df(df)
+    df = pd.concat([df, df_aux], axis=1)
+    if args.create_new_split:
+        df_train, df_test = train_test_split(df, test_size=test_size, stratify=df['labels'], random_state=42)
+    else:
+        print(df['split'].unique())
+        df_train = df[(df['split'] == 'train') | (df['split'] == 'val')]
+        df_test = df[df['split'] == 'test']
+
+    print(f'Num classes: {num_classes}')
+    print(df_train['labels'].value_counts())
+    assert set(df_train['labels'].unique()) == set(df_test['labels'].unique(
+    )), 'The labels for train and test dataframe are different. We recommend to download the dataset again, or to use \
+        the --create-new-split flag'
+    for split, df_split in zip(['train', 'val'],
+                               [df_train, df_test]):
+        fn_out = op.join(dataset_folder, f'fingerspelling_{split}.csv')
+        (df_split.reset_index(drop=True)
+                 .applymap(convert_to_str)
+                 .to_csv(fn_out, index=False))
diff --git a/preprocessing/create_google_asl_landmarks_dataset.py b/preprocessing/create_google_asl_landmarks_dataset.py
index 4a4beda..c128356 100644
--- a/preprocessing/create_google_asl_landmarks_dataset.py
+++ b/preprocessing/create_google_asl_landmarks_dataset.py
@@ -4,6 +4,8 @@ import pandas as pd
 from tqdm.auto import tqdm
 import json
 
+from normalization.blazepose_mapping import map_blazepose_df
+
 def create(train_landmark_files, train_csv, dataset_folder, test_size):
     os.makedirs(dataset_folder, exist_ok=True)
 
@@ -17,15 +19,15 @@ def create(train_landmark_files, train_csv, dataset_folder, test_size):
     mapping = {
             'pose_0': 'nose',
             'pose_1': 'leftEye',
-            'pose_2': 'rightEye',
-            'pose_3': 'leftEar',
-            'pose_4': 'rightEar',
-            'pose_5': 'leftShoulder',
-            'pose_6': 'rightShoulder',
-            'pose_7': 'leftElbow',
-            'pose_8': 'rightElbow',
-            'pose_9': 'leftWrist',
-            'pose_10': 'rightWrist',
+            'pose_4': 'rightEye',
+            'pose_7': 'leftEar',
+            'pose_8': 'rightEar',
+            'pose_11': 'leftShoulder',
+            'pose_12': 'rightShoulder',
+            'pose_13': 'leftElbow',
+            'pose_14': 'rightElbow',
+            'pose_15': 'leftWrist',
+            'pose_16': 'rightWrist',
 
             'left_hand_0': 'wrist_left',
             'left_hand_1': 'thumbCMC_left',
@@ -77,7 +79,7 @@ def create(train_landmark_files, train_csv, dataset_folder, test_size):
         columns.append(f'{v}_X')
         columns.append(f'{v}_Y')
 
-    for _, row in tqdm(train_df.head(6000).iterrows(), total=6000):
+    for _, row in tqdm(train_df.head(10000).iterrows(), total=10000):
         path, participant_id, sequence_id, sign = row['path'], row['participant_id'], row['sequence_id'], row['sign']
         parquet_file = os.path.join(train_landmark_files, str(participant_id), f"{sequence_id}.parquet")
 
@@ -136,6 +138,7 @@ def create(train_landmark_files, train_csv, dataset_folder, test_size):
         video_data.append(new_landmark_data)
 
     video_data = pd.concat(video_data, axis=0, ignore_index=True)
+    video_data = map_blazepose_df(video_data, rename=False)
     video_data.to_csv(os.path.join(dataset_folder, 'spoter.csv'), index=False)
 
 train_landmark_files = 'data/train_landmark_files'
diff --git a/preprocessing/create_wlasl_landmarks_dataset.py b/preprocessing/create_wlasl_landmarks_dataset.py
index c1e4d5c..53d5cf4 100644
--- a/preprocessing/create_wlasl_landmarks_dataset.py
+++ b/preprocessing/create_wlasl_landmarks_dataset.py
@@ -110,6 +110,7 @@ def create(args):
                               'length': length}
                 video_dict.update(video_info)
             video_data.append(video_dict)
+            
     df_video = pd.DataFrame(video_data)
     video_ids = df_video['video_id'].unique()
     lmks_data = []
@@ -126,9 +127,7 @@ def create(args):
         lmks_data.append(lmks_dict)
 
     df_lmks = pd.DataFrame(lmks_data)
-    print(df_lmks)
     df = pd.merge(df_video, df_lmks)
-    print(df)
     aux_columns = ['split', 'video_id', 'labels', 'label_name']
     if videos_folder is not None:
         aux_columns += ['video_width', 'video_height', 'fps', 'length']
diff --git a/preprocessing/extract_mediapipe_landmarks.py b/preprocessing/extract_mediapipe_landmarks.py
index 6d63076..f421919 100644
--- a/preprocessing/extract_mediapipe_landmarks.py
+++ b/preprocessing/extract_mediapipe_landmarks.py
@@ -132,6 +132,12 @@ def extract(args):
         ret, image_orig = cap.read()
         height, width = image_orig.shape[:2]
         landmarks_video = []
+
+        # make sure fps is 20 by determining the number of frames to be skipped
+        frame_rate = int(cap.get(cv2.CAP_PROP_FPS))
+        frame_skip = (frame_rate // 20) - 1
+        
+
         with tqdm(total=int(cap.get(cv2.CAP_PROP_FRAME_COUNT))) as pbar:
             with mp_holistic.Holistic(
                 static_image_mode=False,
@@ -145,6 +151,9 @@ def extract(args):
                         print(e)
                         landmarks = get_landmarks(image_orig, holistic, debug=True)
                     ret, image_orig = cap.read()
+                    for _ in range(frame_skip):
+                        ret, image_orig = cap.read()
+                        pbar.update(1)
                     landmarks_video.append(landmarks)
                     pbar.update(1)
         landmarks_video = np.vstack(landmarks_video)
diff --git a/preprocessing/split_dataset.py b/preprocessing/split_dataset.py
index 17e1f55..3fa13c7 100644
--- a/preprocessing/split_dataset.py
+++ b/preprocessing/split_dataset.py
@@ -8,7 +8,6 @@ dataset = "data/processed/spoter.csv"
 
 # read the dataset
 df = pd.read_csv(dataset)
-df = map_blazepose_df(df)
 
 with open("data/sign_to_prediction_index_map.json", "r") as f:
     sign_to_prediction_index_max = json.load(f)
diff --git a/requirements.txt b/requirements.txt
index 2308b4c..a7d1285 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,7 +1,6 @@
 pandas
 bokeh==2.4.3
 boto3>=1.9
-clearml==1.6.4
 ipywidgets==8.0.4
 matplotlib==3.5.3
 mediapipe==0.8.11
@@ -9,6 +8,7 @@ notebook==6.5.2
 opencv-python==4.6.0.66
 plotly==5.11.0
 scikit-learn==1.0.2
+clearml==1.10.3
 torch
 torchvision
 tqdm==4.54.1
diff --git a/train.py b/train.py
index 76fabfe..1d27a79 100644
--- a/train.py
+++ b/train.py
@@ -15,7 +15,7 @@ from torchvision import transforms
 from torch.utils.data import DataLoader
 from pathlib import Path
 import copy
-
+import numpy as np
 from datasets import CzechSLRDataset, SLREmbeddingDataset, collate_fn_triplet_padd, collate_fn_padd
 from models import SPOTER, SPOTER_EMBEDDINGS, train_epoch, evaluate, train_epoch_embedding, \
     train_epoch_embedding_online, evaluate_embedding
@@ -32,7 +32,7 @@ except ImportError:
     pass
 
 
-PROJECT_NAME = "spoter"
+PROJECT_NAME = "SpoterEmbedding"
 CLEARML = "clearml"
 
 
diff --git a/train.sh b/train.sh
index fe68689..4572863 100755
--- a/train.sh
+++ b/train.sh
@@ -1,22 +1,21 @@
 #!/bin/sh
 python -m train \
 	--save_checkpoints_every 10 \
-    --experiment_name "augment_rotate_75_x8" \
+    --experiment_name "basic" \
     --epochs 300 \
 	--optimizer "ADAM" \
-	--lr 0.001 \
+	--lr 0.0001 \
     --batch_size 16 \
-	--dataset_name "processed" \
+	--dataset_name "GoogleWLASL" \
 	--training_set_path "spoter_train.csv" \
 	--validation_set_path "spoter_test.csv" \
 	--vector_length 32 \
 	--epoch_iters -1 \
-	--scheduler_factor 0 \
-	--hard_triplet_mining "in_batch" \
+	--scheduler_factor 0.2 \
+	--hard_triplet_mining "None" \
 	--filter_easy_triplets \
-	--triplet_loss_margin 1 \
+	--triplet_loss_margin 2 \
 	--dropout 0.2 \
-	--augmentations_prob=0.75 \
-	--hard_mining_scheduler_triplets_threshold=0 \
-	--normalize_embeddings \
-    --num_classes 100 \
\ No newline at end of file
+    --tracker=clearml \
+    --dataset_loader=clearml \
+	--dataset_project="SpoterEmbedding"
diff --git a/visualize_data.ipynb b/visualize_data.ipynb
new file mode 100644
index 0000000..7586303
--- /dev/null
+++ b/visualize_data.ipynb
@@ -0,0 +1,1632 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from augmentations.augment import __preprocess_row_sign"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0 path\n",
+      "1 participant_id\n",
+      "2 sequence_id\n",
+      "3 sign\n",
+      "4 labels\n",
+      "5 nose_X\n",
+      "6 nose_Y\n",
+      "7 leftEye_X\n",
+      "8 leftEye_Y\n",
+      "9 rightEye_X\n",
+      "10 rightEye_Y\n",
+      "11 leftEar_X\n",
+      "12 leftEar_Y\n",
+      "13 rightEar_X\n",
+      "14 rightEar_Y\n",
+      "15 leftShoulder_X\n",
+      "16 leftShoulder_Y\n",
+      "17 rightShoulder_X\n",
+      "18 rightShoulder_Y\n",
+      "19 leftElbow_X\n",
+      "20 leftElbow_Y\n",
+      "21 rightElbow_X\n",
+      "22 rightElbow_Y\n",
+      "23 leftWrist_X\n",
+      "24 leftWrist_Y\n",
+      "25 rightWrist_X\n",
+      "26 rightWrist_Y\n",
+      "27 wrist_left_X\n",
+      "28 wrist_left_Y\n",
+      "29 thumbCMC_left_X\n",
+      "30 thumbCMC_left_Y\n",
+      "31 thumbMP_left_X\n",
+      "32 thumbMP_left_Y\n",
+      "33 thumbIP_left_X\n",
+      "34 thumbIP_left_Y\n",
+      "35 thumbTip_left_X\n",
+      "36 thumbTip_left_Y\n",
+      "37 indexMCP_left_X\n",
+      "38 indexMCP_left_Y\n",
+      "39 indexPIP_left_X\n",
+      "40 indexPIP_left_Y\n",
+      "41 indexDIP_left_X\n",
+      "42 indexDIP_left_Y\n",
+      "43 indexTip_left_X\n",
+      "44 indexTip_left_Y\n",
+      "45 middleMCP_left_X\n",
+      "46 middleMCP_left_Y\n",
+      "47 middlePIP_left_X\n",
+      "48 middlePIP_left_Y\n",
+      "49 middleDIP_left_X\n",
+      "50 middleDIP_left_Y\n",
+      "51 middleTip_left_X\n",
+      "52 middleTip_left_Y\n",
+      "53 ringMCP_left_X\n",
+      "54 ringMCP_left_Y\n",
+      "55 ringPIP_left_X\n",
+      "56 ringPIP_left_Y\n",
+      "57 ringDIP_left_X\n",
+      "58 ringDIP_left_Y\n",
+      "59 ringTip_left_X\n",
+      "60 ringTip_left_Y\n",
+      "61 littleMCP_left_X\n",
+      "62 littleMCP_left_Y\n",
+      "63 littlePIP_left_X\n",
+      "64 littlePIP_left_Y\n",
+      "65 littleDIP_left_X\n",
+      "66 littleDIP_left_Y\n",
+      "67 littleTip_left_X\n",
+      "68 littleTip_left_Y\n",
+      "69 wrist_right_X\n",
+      "70 wrist_right_Y\n",
+      "71 thumbCMC_right_X\n",
+      "72 thumbCMC_right_Y\n",
+      "73 thumbMP_right_X\n",
+      "74 thumbMP_right_Y\n",
+      "75 thumbIP_right_X\n",
+      "76 thumbIP_right_Y\n",
+      "77 thumbTip_right_X\n",
+      "78 thumbTip_right_Y\n",
+      "79 indexMCP_right_X\n",
+      "80 indexMCP_right_Y\n",
+      "81 indexPIP_right_X\n",
+      "82 indexPIP_right_Y\n",
+      "83 indexDIP_right_X\n",
+      "84 indexDIP_right_Y\n",
+      "85 indexTip_right_X\n",
+      "86 indexTip_right_Y\n",
+      "87 middleMCP_right_X\n",
+      "88 middleMCP_right_Y\n",
+      "89 middlePIP_right_X\n",
+      "90 middlePIP_right_Y\n",
+      "91 middleDIP_right_X\n",
+      "92 middleDIP_right_Y\n",
+      "93 middleTip_right_X\n",
+      "94 middleTip_right_Y\n",
+      "95 ringMCP_right_X\n",
+      "96 ringMCP_right_Y\n",
+      "97 ringPIP_right_X\n",
+      "98 ringPIP_right_Y\n",
+      "99 ringDIP_right_X\n",
+      "100 ringDIP_right_Y\n",
+      "101 ringTip_right_X\n",
+      "102 ringTip_right_Y\n",
+      "103 littleMCP_right_X\n",
+      "104 littleMCP_right_Y\n",
+      "105 littlePIP_right_X\n",
+      "106 littlePIP_right_Y\n",
+      "107 littleDIP_right_X\n",
+      "108 littleDIP_right_Y\n",
+      "109 littleTip_right_X\n",
+      "110 littleTip_right_Y\n",
+      "111 neck_X\n",
+      "112 neck_Y\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('data/processed/spoter_train.csv')\n",
+    "for i, e in enumerate(df.columns):\n",
+    "    print(i, e)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# dataset = 'data/processed/spoter_train.csv'\n",
+    "\n",
+    "def plot(dataset):\n",
+    "    df = pd.read_csv(dataset)\n",
+    "    # get columns 0 - 26\n",
+    "    # df = df.iloc[:, 5:27]\n",
+    "\n",
+    "\n",
+    "    # df = df.iloc[:, 27:69]\n",
+    "    # df = df.iloc[:, 69:]\n",
+    "\n",
+    "    if 'wlasl' in dataset:\n",
+    "        df = df.iloc[:, :108]\n",
+    "\n",
+    "    else:\n",
+    "        df = df.iloc[:, 5:]\n",
+    "\n",
+    "\n",
+    "    # get first row\n",
+    "    row = df.iloc[0]\n",
+    "\n",
+    "    # use matplotlib to create a scatter plot (the columns are X, Y, X, Y, X, Y, X, Y)\n",
+    "    import matplotlib.pyplot as plt\n",
+    "    import ast\n",
+    "\n",
+    "    def __process_row(coords):\n",
+    "        coords = coords.tolist()\n",
+    "\n",
+    "        new_coords = []  # string to list\n",
+    "\n",
+    "        for x in coords:\n",
+    "            new_coords.append(ast.literal_eval(x))\n",
+    "\n",
+    "        coords = [x[2] for x in new_coords]\n",
+    "\n",
+    "        return  [float(x) for x in coords]\n",
+    "\n",
+    "\n",
+    "    # extract X and Y coordinates from the row\n",
+    "    x_coords = row.iloc[::2]  # columns 0, 2, 4, 6, ...\n",
+    "    y_coords = row.iloc[1::2] # columns 1, 3, 5, 7, ...\n",
+    "\n",
+    "    x_coords = __process_row(x_coords)\n",
+    "    y_coords = __process_row(y_coords)\n",
+    "\n",
+    "    # create a scatter plot\n",
+    "    plt.scatter(x_coords, y_coords)\n",
+    "\n",
+    "    # add axis labels and a title\n",
+    "    plt.xlabel('X')\n",
+    "    plt.ylabel('Y')\n",
+    "    plt.title('Scatter plot of X and Y coordinates')\n",
+    "\n",
+    "    # show the plot\n",
+    "    plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plot('data/wlasl/WLASL100_train.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plot('data/processed/spoter_train.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[18 19 20 21 22 23 24 25 26 27 28 29 30]\n",
+      "      frame     row_id  type  landmark_index         x         y         z\n",
+      "3801     25  25-face-0  face               0  0.498506  0.494856 -0.018860\n",
+      "3802     25  25-face-1  face               1  0.506121  0.470006 -0.056474\n",
+      "3803     25  25-face-2  face               2  0.505620  0.475341 -0.025482\n",
+      "3804     25  25-face-3  face               3  0.497120  0.439673 -0.049148\n",
+      "3805     25  25-face-4  face               4  0.506552  0.461902 -0.062083\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.plotly.v1+json": {
+       "config": {
+        "plotlyServerURL": "https://plot.ly"
+       },
+       "data": [
+        {
+         "customdata": [
+          [
+           "wrist_left"
+          ],
+          [
+           "thumbCMC_left"
+          ],
+          [
+           "thumbMP_left"
+          ],
+          [
+           "thumbIP_left"
+          ],
+          [
+           "thumbTip_left"
+          ],
+          [
+           "indexMCP_left"
+          ],
+          [
+           "indexPIP_left"
+          ],
+          [
+           "indexDIP_left"
+          ],
+          [
+           "indexTip_left"
+          ],
+          [
+           "middleMCP_left"
+          ],
+          [
+           "middlePIP_left"
+          ],
+          [
+           "middleDIP_left"
+          ],
+          [
+           "middleTip_left"
+          ],
+          [
+           "ringMCP_left"
+          ],
+          [
+           "ringPIP_left"
+          ],
+          [
+           "ringDIP_left"
+          ],
+          [
+           "ringTip_left"
+          ],
+          [
+           "littleMCP_left"
+          ],
+          [
+           "littlePIP_left"
+          ],
+          [
+           "littleDIP_left"
+          ],
+          [
+           "littleTip_left"
+          ]
+         ],
+         "hovertemplate": "type=left_hand<br>x=%{x}<br>y=%{y}<br>name=%{customdata[0]}<extra></extra>",
+         "legendgroup": "left_hand",
+         "marker": {
+          "color": "#636efa",
+          "symbol": "circle"
+         },
+         "mode": "markers",
+         "name": "left_hand",
+         "orientation": "v",
+         "showlegend": true,
+         "type": "scatter",
+         "x": [
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null
+         ],
+         "xaxis": "x",
+         "y": [
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null,
+          null
+         ],
+         "yaxis": "y"
+        },
+        {
+         "customdata": [
+          [
+           "nose"
+          ],
+          [
+           "leftEye"
+          ],
+          [
+           "rightEye"
+          ],
+          [
+           "leftEar"
+          ],
+          [
+           "rightEar"
+          ],
+          [
+           "leftShoulder"
+          ],
+          [
+           "rightShoulder"
+          ],
+          [
+           "leftElbow"
+          ],
+          [
+           "rightElbow"
+          ],
+          [
+           "leftWrist"
+          ],
+          [
+           "rightWrist"
+          ]
+         ],
+         "hovertemplate": "type=pose<br>x=%{x}<br>y=%{y}<br>name=%{customdata[0]}<extra></extra>",
+         "legendgroup": "pose",
+         "marker": {
+          "color": "#EF553B",
+          "symbol": "circle"
+         },
+         "mode": "markers",
+         "name": "pose",
+         "orientation": "v",
+         "showlegend": true,
+         "type": "scatter",
+         "x": [
+          0.5037816762924194,
+          0.544114351272583,
+          0.47258099913597107,
+          0.6112894415855408,
+          0.42202046513557434,
+          0.790356457233429,
+          0.30560430884361267,
+          0.8586887121200562,
+          0.052559275180101395,
+          0.8901190161705017,
+          0.14568309485912323
+         ],
+         "xaxis": "x",
+         "y": [
+          0.5385957062244415,
+          0.5870676934719086,
+          0.5835375487804413,
+          0.5667203366756439,
+          0.5620827376842499,
+          0.3601607084274292,
+          0.3561617136001587,
+          0.10383915901184082,
+          0.12815016508102417,
+          -0.1593785285949707,
+          0.4648846983909607
+         ],
+         "yaxis": "y"
+        },
+        {
+         "customdata": [
+          [
+           "wrist_right"
+          ],
+          [
+           "thumbCMC_right"
+          ],
+          [
+           "thumbMP_right"
+          ],
+          [
+           "thumbIP_right"
+          ],
+          [
+           "thumbTip_right"
+          ],
+          [
+           "indexMCP_right"
+          ],
+          [
+           "indexPIP_right"
+          ],
+          [
+           "indexDIP_right"
+          ],
+          [
+           "indexTip_right"
+          ],
+          [
+           "middleMCP_right"
+          ],
+          [
+           "middlePIP_right"
+          ],
+          [
+           "middleDIP_right"
+          ],
+          [
+           "middleTip_right"
+          ],
+          [
+           "ringMCP_right"
+          ],
+          [
+           "ringPIP_right"
+          ],
+          [
+           "ringDIP_right"
+          ],
+          [
+           "ringTip_right"
+          ],
+          [
+           "littleMCP_right"
+          ],
+          [
+           "littlePIP_right"
+          ],
+          [
+           "littleDIP_right"
+          ],
+          [
+           "littleTip_right"
+          ]
+         ],
+         "hovertemplate": "type=right_hand<br>x=%{x}<br>y=%{y}<br>name=%{customdata[0]}<extra></extra>",
+         "legendgroup": "right_hand",
+         "marker": {
+          "color": "#00cc96",
+          "symbol": "circle"
+         },
+         "mode": "markers",
+         "name": "right_hand",
+         "orientation": "v",
+         "showlegend": true,
+         "type": "scatter",
+         "x": [
+          0.1788196861743927,
+          0.23843127489089966,
+          0.25467628240585327,
+          0.27044928073883057,
+          0.2871263027191162,
+          0.19056828320026398,
+          0.2649158835411072,
+          0.3157113492488861,
+          0.3494824171066284,
+          0.18622460961341858,
+          0.2733367681503296,
+          0.32277774810791016,
+          0.3569425642490387,
+          0.19574135541915894,
+          0.2806362509727478,
+          0.3286181688308716,
+          0.36066585779190063,
+          0.21657982468605042,
+          0.2816353738307953,
+          0.31945061683654785,
+          0.34714818000793457
+         ],
+         "xaxis": "x",
+         "y": [
+          0.4631972312927246,
+          0.49802637100219727,
+          0.5355206429958344,
+          0.5633883774280548,
+          0.5824070870876312,
+          0.5867454409599304,
+          0.6103077828884125,
+          0.6078206300735474,
+          0.6010101139545441,
+          0.5849654078483582,
+          0.6130928993225098,
+          0.6087997257709503,
+          0.6008164584636688,
+          0.5775772035121918,
+          0.6042222082614899,
+          0.6019154489040375,
+          0.5936585664749146,
+          0.564491868019104,
+          0.5853257775306702,
+          0.5884504020214081,
+          0.5863424837589264
+         ],
+         "yaxis": "y"
+        }
+       ],
+       "layout": {
+        "legend": {
+         "title": {
+          "text": "type"
+         },
+         "tracegroupgap": 0
+        },
+        "margin": {
+         "t": 60
+        },
+        "template": {
+         "data": {
+          "bar": [
+           {
+            "error_x": {
+             "color": "#2a3f5f"
+            },
+            "error_y": {
+             "color": "#2a3f5f"
+            },
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "bar"
+           }
+          ],
+          "barpolar": [
+           {
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "barpolar"
+           }
+          ],
+          "carpet": [
+           {
+            "aaxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "baxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "type": "carpet"
+           }
+          ],
+          "choropleth": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "choropleth"
+           }
+          ],
+          "contour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "contour"
+           }
+          ],
+          "contourcarpet": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "contourcarpet"
+           }
+          ],
+          "heatmap": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmap"
+           }
+          ],
+          "heatmapgl": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmapgl"
+           }
+          ],
+          "histogram": [
+           {
+            "marker": {
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "histogram"
+           }
+          ],
+          "histogram2d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2d"
+           }
+          ],
+          "histogram2dcontour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2dcontour"
+           }
+          ],
+          "mesh3d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "mesh3d"
+           }
+          ],
+          "parcoords": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "parcoords"
+           }
+          ],
+          "pie": [
+           {
+            "automargin": true,
+            "type": "pie"
+           }
+          ],
+          "scatter": [
+           {
+            "fillpattern": {
+             "fillmode": "overlay",
+             "size": 10,
+             "solidity": 0.2
+            },
+            "type": "scatter"
+           }
+          ],
+          "scatter3d": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatter3d"
+           }
+          ],
+          "scattercarpet": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattercarpet"
+           }
+          ],
+          "scattergeo": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergeo"
+           }
+          ],
+          "scattergl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergl"
+           }
+          ],
+          "scattermapbox": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattermapbox"
+           }
+          ],
+          "scatterpolar": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolar"
+           }
+          ],
+          "scatterpolargl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolargl"
+           }
+          ],
+          "scatterternary": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterternary"
+           }
+          ],
+          "surface": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "surface"
+           }
+          ],
+          "table": [
+           {
+            "cells": {
+             "fill": {
+              "color": "#EBF0F8"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "header": {
+             "fill": {
+              "color": "#C8D4E3"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "type": "table"
+           }
+          ]
+         },
+         "layout": {
+          "annotationdefaults": {
+           "arrowcolor": "#2a3f5f",
+           "arrowhead": 0,
+           "arrowwidth": 1
+          },
+          "autotypenumbers": "strict",
+          "coloraxis": {
+           "colorbar": {
+            "outlinewidth": 0,
+            "ticks": ""
+           }
+          },
+          "colorscale": {
+           "diverging": [
+            [
+             0,
+             "#8e0152"
+            ],
+            [
+             0.1,
+             "#c51b7d"
+            ],
+            [
+             0.2,
+             "#de77ae"
+            ],
+            [
+             0.3,
+             "#f1b6da"
+            ],
+            [
+             0.4,
+             "#fde0ef"
+            ],
+            [
+             0.5,
+             "#f7f7f7"
+            ],
+            [
+             0.6,
+             "#e6f5d0"
+            ],
+            [
+             0.7,
+             "#b8e186"
+            ],
+            [
+             0.8,
+             "#7fbc41"
+            ],
+            [
+             0.9,
+             "#4d9221"
+            ],
+            [
+             1,
+             "#276419"
+            ]
+           ],
+           "sequential": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ],
+           "sequentialminus": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ]
+          },
+          "colorway": [
+           "#636efa",
+           "#EF553B",
+           "#00cc96",
+           "#ab63fa",
+           "#FFA15A",
+           "#19d3f3",
+           "#FF6692",
+           "#B6E880",
+           "#FF97FF",
+           "#FECB52"
+          ],
+          "font": {
+           "color": "#2a3f5f"
+          },
+          "geo": {
+           "bgcolor": "white",
+           "lakecolor": "white",
+           "landcolor": "#E5ECF6",
+           "showlakes": true,
+           "showland": true,
+           "subunitcolor": "white"
+          },
+          "hoverlabel": {
+           "align": "left"
+          },
+          "hovermode": "closest",
+          "mapbox": {
+           "style": "light"
+          },
+          "paper_bgcolor": "white",
+          "plot_bgcolor": "#E5ECF6",
+          "polar": {
+           "angularaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "radialaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "scene": {
+           "xaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "yaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "zaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           }
+          },
+          "shapedefaults": {
+           "line": {
+            "color": "#2a3f5f"
+           }
+          },
+          "ternary": {
+           "aaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "baxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "caxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "title": {
+           "x": 0.05
+          },
+          "xaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          },
+          "yaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          }
+         }
+        },
+        "xaxis": {
+         "anchor": "y",
+         "constrain": "domain",
+         "domain": [
+          0,
+          1
+         ],
+         "range": [
+          0,
+          1
+         ],
+         "title": {
+          "text": "x"
+         }
+        },
+        "yaxis": {
+         "anchor": "x",
+         "domain": [
+          0,
+          1
+         ],
+         "range": [
+          0,
+          1
+         ],
+         "scaleanchor": "x",
+         "scaleratio": 1,
+         "title": {
+          "text": "y"
+         }
+        }
+       }
+      },
+      "text/html": [
+       "<div>                            <div id=\"8f1cccf1-52ac-4cf0-8409-1c18e66d17c3\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"8f1cccf1-52ac-4cf0-8409-1c18e66d17c3\")) {                    Plotly.newPlot(                        \"8f1cccf1-52ac-4cf0-8409-1c18e66d17c3\",                        [{\"customdata\":[[\"wrist_left\"],[\"thumbCMC_left\"],[\"thumbMP_left\"],[\"thumbIP_left\"],[\"thumbTip_left\"],[\"indexMCP_left\"],[\"indexPIP_left\"],[\"indexDIP_left\"],[\"indexTip_left\"],[\"middleMCP_left\"],[\"middlePIP_left\"],[\"middleDIP_left\"],[\"middleTip_left\"],[\"ringMCP_left\"],[\"ringPIP_left\"],[\"ringDIP_left\"],[\"ringTip_left\"],[\"littleMCP_left\"],[\"littlePIP_left\"],[\"littleDIP_left\"],[\"littleTip_left\"]],\"hovertemplate\":\"type=left_hand<br>x=%{x}<br>y=%{y}<br>name=%{customdata[0]}<extra></extra>\",\"legendgroup\":\"left_hand\",\"marker\":{\"color\":\"#636efa\",\"symbol\":\"circle\"},\"mode\":\"markers\",\"name\":\"left_hand\",\"orientation\":\"v\",\"showlegend\":true,\"x\":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],\"xaxis\":\"x\",\"y\":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],\"yaxis\":\"y\",\"type\":\"scatter\"},{\"customdata\":[[\"nose\"],[\"leftEye\"],[\"rightEye\"],[\"leftEar\"],[\"rightEar\"],[\"leftShoulder\"],[\"rightShoulder\"],[\"leftElbow\"],[\"rightElbow\"],[\"leftWrist\"],[\"rightWrist\"]],\"hovertemplate\":\"type=pose<br>x=%{x}<br>y=%{y}<br>name=%{customdata[0]}<extra></extra>\",\"legendgroup\":\"pose\",\"marker\":{\"color\":\"#EF553B\",\"symbol\":\"circle\"},\"mode\":\"markers\",\"name\":\"pose\",\"orientation\":\"v\",\"showlegend\":true,\"x\":[0.5037816762924194,0.544114351272583,0.47258099913597107,0.6112894415855408,0.42202046513557434,0.790356457233429,0.30560430884361267,0.8586887121200562,0.052559275180101395,0.8901190161705017,0.14568309485912323],\"xaxis\":\"x\",\"y\":[0.5385957062244415,0.5870676934719086,0.5835375487804413,0.5667203366756439,0.5620827376842499,0.3601607084274292,0.3561617136001587,0.10383915901184082,0.12815016508102417,-0.1593785285949707,0.4648846983909607],\"yaxis\":\"y\",\"type\":\"scatter\"},{\"customdata\":[[\"wrist_right\"],[\"thumbCMC_right\"],[\"thumbMP_right\"],[\"thumbIP_right\"],[\"thumbTip_right\"],[\"indexMCP_right\"],[\"indexPIP_right\"],[\"indexDIP_right\"],[\"indexTip_right\"],[\"middleMCP_right\"],[\"middlePIP_right\"],[\"middleDIP_right\"],[\"middleTip_right\"],[\"ringMCP_right\"],[\"ringPIP_right\"],[\"ringDIP_right\"],[\"ringTip_right\"],[\"littleMCP_right\"],[\"littlePIP_right\"],[\"littleDIP_right\"],[\"littleTip_right\"]],\"hovertemplate\":\"type=right_hand<br>x=%{x}<br>y=%{y}<br>name=%{customdata[0]}<extra></extra>\",\"legendgroup\":\"right_hand\",\"marker\":{\"color\":\"#00cc96\",\"symbol\":\"circle\"},\"mode\":\"markers\",\"name\":\"right_hand\",\"orientation\":\"v\",\"showlegend\":true,\"x\":[0.1788196861743927,0.23843127489089966,0.25467628240585327,0.27044928073883057,0.2871263027191162,0.19056828320026398,0.2649158835411072,0.3157113492488861,0.3494824171066284,0.18622460961341858,0.2733367681503296,0.32277774810791016,0.3569425642490387,0.19574135541915894,0.2806362509727478,0.3286181688308716,0.36066585779190063,0.21657982468605042,0.2816353738307953,0.31945061683654785,0.34714818000793457],\"xaxis\":\"x\",\"y\":[0.4631972312927246,0.49802637100219727,0.5355206429958344,0.5633883774280548,0.5824070870876312,0.5867454409599304,0.6103077828884125,0.6078206300735474,0.6010101139545441,0.5849654078483582,0.6130928993225098,0.6087997257709503,0.6008164584636688,0.5775772035121918,0.6042222082614899,0.6019154489040375,0.5936585664749146,0.564491868019104,0.5853257775306702,0.5884504020214081,0.5863424837589264],\"yaxis\":\"y\",\"type\":\"scatter\"}],                        {\"template\":{\"data\":{\"histogram2dcontour\":[{\"type\":\"histogram2dcontour\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"choropleth\":[{\"type\":\"choropleth\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"histogram2d\":[{\"type\":\"histogram2d\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"heatmap\":[{\"type\":\"heatmap\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"heatmapgl\":[{\"type\":\"heatmapgl\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"contourcarpet\":[{\"type\":\"contourcarpet\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"contour\":[{\"type\":\"contour\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"surface\":[{\"type\":\"surface\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"mesh3d\":[{\"type\":\"mesh3d\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"scatter\":[{\"fillpattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2},\"type\":\"scatter\"}],\"parcoords\":[{\"type\":\"parcoords\",\"line\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterpolargl\":[{\"type\":\"scatterpolargl\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"bar\":[{\"error_x\":{\"color\":\"#2a3f5f\"},\"error_y\":{\"color\":\"#2a3f5f\"},\"marker\":{\"line\":{\"color\":\"#E5ECF6\",\"width\":0.5},\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"bar\"}],\"scattergeo\":[{\"type\":\"scattergeo\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterpolar\":[{\"type\":\"scatterpolar\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"histogram\":[{\"marker\":{\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"histogram\"}],\"scattergl\":[{\"type\":\"scattergl\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatter3d\":[{\"type\":\"scatter3d\",\"line\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}},\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scattermapbox\":[{\"type\":\"scattermapbox\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterternary\":[{\"type\":\"scatterternary\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scattercarpet\":[{\"type\":\"scattercarpet\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"carpet\":[{\"aaxis\":{\"endlinecolor\":\"#2a3f5f\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"minorgridcolor\":\"white\",\"startlinecolor\":\"#2a3f5f\"},\"baxis\":{\"endlinecolor\":\"#2a3f5f\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"minorgridcolor\":\"white\",\"startlinecolor\":\"#2a3f5f\"},\"type\":\"carpet\"}],\"table\":[{\"cells\":{\"fill\":{\"color\":\"#EBF0F8\"},\"line\":{\"color\":\"white\"}},\"header\":{\"fill\":{\"color\":\"#C8D4E3\"},\"line\":{\"color\":\"white\"}},\"type\":\"table\"}],\"barpolar\":[{\"marker\":{\"line\":{\"color\":\"#E5ECF6\",\"width\":0.5},\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"barpolar\"}],\"pie\":[{\"automargin\":true,\"type\":\"pie\"}]},\"layout\":{\"autotypenumbers\":\"strict\",\"colorway\":[\"#636efa\",\"#EF553B\",\"#00cc96\",\"#ab63fa\",\"#FFA15A\",\"#19d3f3\",\"#FF6692\",\"#B6E880\",\"#FF97FF\",\"#FECB52\"],\"font\":{\"color\":\"#2a3f5f\"},\"hovermode\":\"closest\",\"hoverlabel\":{\"align\":\"left\"},\"paper_bgcolor\":\"white\",\"plot_bgcolor\":\"#E5ECF6\",\"polar\":{\"bgcolor\":\"#E5ECF6\",\"angularaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"radialaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"}},\"ternary\":{\"bgcolor\":\"#E5ECF6\",\"aaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"baxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"caxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"}},\"coloraxis\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}},\"colorscale\":{\"sequential\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]],\"sequentialminus\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]],\"diverging\":[[0,\"#8e0152\"],[0.1,\"#c51b7d\"],[0.2,\"#de77ae\"],[0.3,\"#f1b6da\"],[0.4,\"#fde0ef\"],[0.5,\"#f7f7f7\"],[0.6,\"#e6f5d0\"],[0.7,\"#b8e186\"],[0.8,\"#7fbc41\"],[0.9,\"#4d9221\"],[1,\"#276419\"]]},\"xaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\",\"title\":{\"standoff\":15},\"zerolinecolor\":\"white\",\"automargin\":true,\"zerolinewidth\":2},\"yaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\",\"title\":{\"standoff\":15},\"zerolinecolor\":\"white\",\"automargin\":true,\"zerolinewidth\":2},\"scene\":{\"xaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2},\"yaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2},\"zaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2}},\"shapedefaults\":{\"line\":{\"color\":\"#2a3f5f\"}},\"annotationdefaults\":{\"arrowcolor\":\"#2a3f5f\",\"arrowhead\":0,\"arrowwidth\":1},\"geo\":{\"bgcolor\":\"white\",\"landcolor\":\"#E5ECF6\",\"subunitcolor\":\"white\",\"showland\":true,\"showlakes\":true,\"lakecolor\":\"white\"},\"title\":{\"x\":0.05},\"mapbox\":{\"style\":\"light\"}}},\"xaxis\":{\"anchor\":\"y\",\"domain\":[0.0,1.0],\"title\":{\"text\":\"x\"},\"range\":[0,1],\"constrain\":\"domain\"},\"yaxis\":{\"anchor\":\"x\",\"domain\":[0.0,1.0],\"title\":{\"text\":\"y\"},\"scaleanchor\":\"x\",\"scaleratio\":1,\"range\":[0,1]},\"legend\":{\"title\":{\"text\":\"type\"},\"tracegroupgap\":0},\"margin\":{\"t\":60}},                        {\"responsive\": true}                    ).then(function(){\n",
+       "                            \n",
+       "var gd = document.getElementById('8f1cccf1-52ac-4cf0-8409-1c18e66d17c3');\n",
+       "var x = new MutationObserver(function (mutations, observer) {{\n",
+       "        var display = window.getComputedStyle(gd).display;\n",
+       "        if (!display || display === 'none') {{\n",
+       "            console.log([gd, 'removed!']);\n",
+       "            Plotly.purge(gd);\n",
+       "            observer.disconnect();\n",
+       "        }}\n",
+       "}});\n",
+       "\n",
+       "// Listen for the removal of the full notebook cells\n",
+       "var notebookContainer = gd.closest('#notebook-container');\n",
+       "if (notebookContainer) {{\n",
+       "    x.observe(notebookContainer, {childList: true});\n",
+       "}}\n",
+       "\n",
+       "// Listen for the clearing of the current output cell\n",
+       "var outputEl = gd.closest('.output');\n",
+       "if (outputEl) {{\n",
+       "    x.observe(outputEl, {childList: true});\n",
+       "}}\n",
+       "\n",
+       "                        })                };                });            </script>        </div>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# read parquet file at data/train_landmark_files/2044/635217.parquet\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "df = pd.read_parquet('data/train_landmark_files/37779/254554888.parquet')\n",
+    "\n",
+    "# print all unique frame numbers\n",
+    "print(df['frame'].unique())\n",
+    "\n",
+    "# filter where type is pose\n",
+    "df = df[df['frame'] == 25]\n",
+    "\n",
+    "print(df.head())\n",
+    "\n",
+    "mapping = {\n",
+    "            'pose_0': 'nose',\n",
+    "            'pose_1': 'leftEye',\n",
+    "            'pose_4': 'rightEye',\n",
+    "            'pose_7': 'leftEar',\n",
+    "            'pose_8': 'rightEar',\n",
+    "            'pose_11': 'leftShoulder',\n",
+    "            'pose_12': 'rightShoulder',\n",
+    "            'pose_13': 'leftElbow',\n",
+    "            'pose_14': 'rightElbow',\n",
+    "            'pose_15': 'leftWrist',\n",
+    "            'pose_16': 'rightWrist',\n",
+    "\n",
+    "            'left_hand_0': 'wrist_left',\n",
+    "            'left_hand_1': 'thumbCMC_left',\n",
+    "            'left_hand_2': 'thumbMP_left',\n",
+    "            'left_hand_3': 'thumbIP_left',\n",
+    "            'left_hand_4': 'thumbTip_left',\n",
+    "            'left_hand_5': 'indexMCP_left',\n",
+    "            'left_hand_6': 'indexPIP_left',\n",
+    "            'left_hand_7': 'indexDIP_left',\n",
+    "            'left_hand_8': 'indexTip_left',\n",
+    "            'left_hand_9': 'middleMCP_left',\n",
+    "            'left_hand_10': 'middlePIP_left',\n",
+    "            'left_hand_11': 'middleDIP_left',\n",
+    "            'left_hand_12': 'middleTip_left',\n",
+    "            'left_hand_13': 'ringMCP_left',\n",
+    "            'left_hand_14': 'ringPIP_left',\n",
+    "            'left_hand_15': 'ringDIP_left',\n",
+    "            'left_hand_16': 'ringTip_left',\n",
+    "            'left_hand_17': 'littleMCP_left',\n",
+    "            'left_hand_18': 'littlePIP_left',\n",
+    "            'left_hand_19': 'littleDIP_left',\n",
+    "            'left_hand_20': 'littleTip_left',\n",
+    "\n",
+    "            'right_hand_0': 'wrist_right',\n",
+    "            'right_hand_1': 'thumbCMC_right',\n",
+    "            'right_hand_2': 'thumbMP_right',\n",
+    "            'right_hand_3': 'thumbIP_right',\n",
+    "            'right_hand_4': 'thumbTip_right',\n",
+    "            'right_hand_5': 'indexMCP_right',\n",
+    "            'right_hand_6': 'indexPIP_right',\n",
+    "            'right_hand_7': 'indexDIP_right',\n",
+    "            'right_hand_8': 'indexTip_right',\n",
+    "            'right_hand_9': 'middleMCP_right',\n",
+    "            'right_hand_10': 'middlePIP_right',\n",
+    "            'right_hand_11': 'middleDIP_right',\n",
+    "            'right_hand_12': 'middleTip_right',\n",
+    "            'right_hand_13': 'ringMCP_right',\n",
+    "            'right_hand_14': 'ringPIP_right',\n",
+    "            'right_hand_15': 'ringDIP_right',\n",
+    "            'right_hand_16': 'ringTip_right',\n",
+    "            'right_hand_17': 'littleMCP_right',\n",
+    "            'right_hand_18': 'littlePIP_right',\n",
+    "            'right_hand_19': 'littleDIP_right',\n",
+    "            'right_hand_20': 'littleTip_right',\n",
+    "        }\n",
+    "\n",
+    "# scatter plot and when hovering over the point, show the frame number\n",
+    "import plotly.express as px\n",
+    "\n",
+    "# combine type and landmark index\n",
+    "df['landmark_id'] = df['type'] + '_' + df['landmark_index'].astype(str)\n",
+    "# only keep rows where landmark_id is in the mapping\n",
+    "df = df[df['landmark_id'].isin(mapping.keys())]\n",
+    "df['name'] = df['landmark_id'].apply(lambda x: mapping[x])\n",
+    "\n",
+    "# flip vertically\n",
+    "df['y'] = 1 - df['y']\n",
+    "\n",
+    "# keep aspect ratio\n",
+    "\n",
+    "# scatter with px and set color of points based on the type\n",
+    "fig = px.scatter(df, x='x', y='y', color='type', hover_data=['name'])\n",
+    "\n",
+    "fig.update_xaxes(range=[0, 1], constrain='domain')\n",
+    "fig.update_yaxes(scaleanchor='x', scaleratio=1, range=[0, 1])\n",
+    "\n",
+    "# show the plot\n",
+    "fig.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from training dataset\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}