Adding new time evolution graph of mean dist gap for all markets

app.py

@@ -4,11 +4,12 @@ import pandas as pd
 import duckdb
 import logging
 
-from tabs.tokens_pwc_dist import (
+from olas_predict_live_markets.tabs.tokens_dist import (
     get_extreme_cases,
 )
 from tabs.dist_gap import (
     get_distribution_plot,
+    get_avg_gap_time_evolution,
     get_correlation_map,
     get_kde_with_trades,
     get_kde_with_total_bet_amount,
@@ -76,16 +77,6 @@ with demo:
                     f"Market id = {best_market_id} Dist gap = {round(best_gap,2)}"
                 )
             with gr.Row():
-                # with gr.Column(min_width=350):
-                #     gr.Markdown("# Evolution of outcomes probability based on tokens")
-                #     best_market_tokens_dist = get_based_tokens_distribution(
-                #         best_market_id, live_markets_data
-                #     )
-                # with gr.Column(min_width=350):
-                #     gr.Markdown("# Evolution of outcomes probability based on votes")
-                #     best_market_votes_dist = get_based_votes_distribution(
-                #         best_market_id, live_markets_data
-                #     )
                 best_case = get_dist_gap_time_evolution(
                     best_market_id, live_markets_data
                 )
@@ -98,19 +89,16 @@ with demo:
                 )
 
             with gr.Row():
-                # with gr.Column(min_width=350):
-                #     # gr.Markdown("# Evolution of outcomes probability based on tokens")
-                #     worst_market_tokens_dist = get_based_tokens_distribution(
-                #         worst_market_id, live_markets_data
-                #     )
-                # with gr.Column(min_width=350):
-                #     worst_market_votes_dist = get_based_votes_distribution(
-                #         worst_market_id, live_markets_data
-                #     )
-
                 worst_case = get_dist_gap_time_evolution(
                     worst_market_id, live_markets_data
                 )
+            with gr.Row():
+                gr.Markdown(
+                    "Time evolution of the average distribution gap percentage of all markets"
+                )
+
+            with gr.Row():
+                mean_plot = get_avg_gap_time_evolution(markets_data)
 
         with gr.TabItem("📏 Distribution gap metric for all markets"):
             # remove samples with no trades

notebooks/analysis_of_markets_data.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
@@ -49,8 +49,6 @@
        "      <th>open</th>\n",
        "      <th>total_trades</th>\n",
        "      <th>...</th>\n",
-       "      <th>votes_second_outcome_perc</th>\n",
-       "      <th>first_outcome</th>\n",
        "      <th>second_outcome</th>\n",
        "      <th>sample_datetime</th>\n",
        "      <th>first_token_perc</th>\n",
@@ -59,6 +57,8 @@
        "      <th>total_bet_amount</th>\n",
        "      <th>price_weighted_first_outcome_perc</th>\n",
        "      <th>price_weighted_second_outcome_perc</th>\n",
+       "      <th>bought_tokens_first_perc</th>\n",
+       "      <th>bought_tokens_second_perc</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -66,121 +66,121 @@
        "      <th>0</th>\n",
        "      <td>1724201135</td>\n",
        "      <td>0x241d212b45ae3ecb2809421df1f3cff2bb2988f0</td>\n",
-       "      <td>6851416565110943855</td>\n",
-       "      <td>7000000000000000005</td>\n",
+       "      <td>6861664707883062434</td>\n",
+       "      <td>7000000000000000008</td>\n",
        "      <td>1724630400</td>\n",
-       "      <td>[5686089254551548648, 8617522132769359689]</td>\n",
+       "      <td>[5728447658624505774, 8553800771178854358]</td>\n",
        "      <td>Will SpaceX successfully send four people on a...</td>\n",
-       "      <td>1724248530</td>\n",
+       "      <td>1724320709</td>\n",
        "      <td>True</td>\n",
-       "      <td>14</td>\n",
+       "      <td>25</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>Yes</td>\n",
        "      <td>No</td>\n",
-       "      <td>2024-08-21 15:55:30</td>\n",
-       "      <td>60.25</td>\n",
-       "      <td>39.75</td>\n",
-       "      <td>0.374714</td>\n",
-       "      <td>5.246</td>\n",
-       "      <td>67.42</td>\n",
-       "      <td>32.58</td>\n",
+       "      <td>2024-08-22 11:58:29</td>\n",
+       "      <td>59.89</td>\n",
+       "      <td>40.11</td>\n",
+       "      <td>0.398600</td>\n",
+       "      <td>9.965</td>\n",
+       "      <td>62.67</td>\n",
+       "      <td>37.33</td>\n",
+       "      <td>57.34</td>\n",
+       "      <td>42.66</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>1724199465</td>\n",
-       "      <td>0x320f9768e0fe0d328a9a2c8464f12959b16e5194</td>\n",
-       "      <td>5879350969765507881</td>\n",
-       "      <td>7000000000000000002</td>\n",
-       "      <td>1724630400</td>\n",
-       "      <td>[3811004712840132698, 12857501811768421751]</td>\n",
-       "      <td>Will the World War II-era bomb in Northern Ire...</td>\n",
-       "      <td>1724248530</td>\n",
+       "      <td>1724286555</td>\n",
+       "      <td>0x2ed5a1a207b1e9b1c17a1c2baf64647c3db9d1f6</td>\n",
+       "      <td>6764194343046296637</td>\n",
+       "      <td>7000000000000000001</td>\n",
+       "      <td>1724716800</td>\n",
+       "      <td>[9108406198169923801, 5379645893465440960]</td>\n",
+       "      <td>Will there be a significant increase in the pu...</td>\n",
+       "      <td>1724320709</td>\n",
        "      <td>True</td>\n",
-       "      <td>5</td>\n",
+       "      <td>6</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>Yes</td>\n",
        "      <td>No</td>\n",
-       "      <td>2024-08-21 15:55:30</td>\n",
-       "      <td>77.14</td>\n",
-       "      <td>22.86</td>\n",
-       "      <td>1.195400</td>\n",
-       "      <td>5.977</td>\n",
-       "      <td>100.00</td>\n",
-       "      <td>0.00</td>\n",
+       "      <td>2024-08-22 11:58:29</td>\n",
+       "      <td>37.13</td>\n",
+       "      <td>62.87</td>\n",
+       "      <td>0.411333</td>\n",
+       "      <td>2.468</td>\n",
+       "      <td>6.48</td>\n",
+       "      <td>93.52</td>\n",
+       "      <td>7.13</td>\n",
+       "      <td>92.87</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>1724155795</td>\n",
-       "      <td>0x34accb10e7034a8de32bacd17fe56eff48286673</td>\n",
-       "      <td>6390071369907879264</td>\n",
+       "      <td>1724199465</td>\n",
+       "      <td>0x320f9768e0fe0d328a9a2c8464f12959b16e5194</td>\n",
+       "      <td>5657370332642200804</td>\n",
        "      <td>7000000000000000003</td>\n",
-       "      <td>1724371200</td>\n",
-       "      <td>[4537576918801928698, 10798715013945731768]</td>\n",
-       "      <td>Will James Anderson retire from his cricket ca...</td>\n",
-       "      <td>1724248530</td>\n",
+       "      <td>1724630400</td>\n",
+       "      <td>[3560526624520056083, 13762009154082647147]</td>\n",
+       "      <td>Will the World War II-era bomb in Northern Ire...</td>\n",
+       "      <td>1724320709</td>\n",
        "      <td>True</td>\n",
-       "      <td>9</td>\n",
+       "      <td>6</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>Yes</td>\n",
        "      <td>No</td>\n",
-       "      <td>2024-08-21 15:55:30</td>\n",
-       "      <td>70.41</td>\n",
-       "      <td>29.59</td>\n",
-       "      <td>0.739667</td>\n",
-       "      <td>6.657</td>\n",
-       "      <td>86.01</td>\n",
-       "      <td>13.99</td>\n",
+       "      <td>2024-08-22 11:58:29</td>\n",
+       "      <td>79.45</td>\n",
+       "      <td>20.55</td>\n",
+       "      <td>1.150000</td>\n",
+       "      <td>6.900</td>\n",
+       "      <td>100.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>100.00</td>\n",
+       "      <td>0.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>1724199065</td>\n",
-       "      <td>0x443248919f03c00d497f84d533545d2a498d6b85</td>\n",
-       "      <td>6953917419955440631</td>\n",
+       "      <td>1724287075</td>\n",
+       "      <td>0x3c4a1acefa3049f6de2b212fa3141f46b0b5823f</td>\n",
+       "      <td>6755535026140294583</td>\n",
        "      <td>7000000000000000001</td>\n",
-       "      <td>1724630400</td>\n",
-       "      <td>[7853595072000897778, 6239180852943572619]</td>\n",
-       "      <td>Will the Texas jury decide the liability of th...</td>\n",
-       "      <td>1724248530</td>\n",
+       "      <td>1724716800</td>\n",
+       "      <td>[5353172588127988920, 9153450443325863452]</td>\n",
+       "      <td>Will the human remains found on the Michigan m...</td>\n",
+       "      <td>1724320709</td>\n",
        "      <td>True</td>\n",
-       "      <td>2</td>\n",
+       "      <td>4</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>Yes</td>\n",
        "      <td>No</td>\n",
-       "      <td>2024-08-21 15:55:30</td>\n",
-       "      <td>44.27</td>\n",
-       "      <td>55.73</td>\n",
-       "      <td>1.374000</td>\n",
-       "      <td>2.748</td>\n",
-       "      <td>36.39</td>\n",
-       "      <td>63.61</td>\n",
+       "      <td>2024-08-22 11:58:29</td>\n",
+       "      <td>63.10</td>\n",
+       "      <td>36.90</td>\n",
+       "      <td>0.628500</td>\n",
+       "      <td>2.514</td>\n",
+       "      <td>93.64</td>\n",
+       "      <td>6.36</td>\n",
+       "      <td>92.98</td>\n",
+       "      <td>7.02</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>1724154665</td>\n",
-       "      <td>0x4aad7221a6d8dd3b9c596446d2d079276befe3da</td>\n",
-       "      <td>6342175206935951613</td>\n",
-       "      <td>7000000000000000003</td>\n",
-       "      <td>1724457600</td>\n",
-       "      <td>[10995908979010407929, 4456202765367908944]</td>\n",
-       "      <td>Will Ukraine launch another strike inside Russ...</td>\n",
-       "      <td>1724248530</td>\n",
+       "      <td>1724285320</td>\n",
+       "      <td>0x3fc60512d8fff2a565155ee05aef0d2a79fcec23</td>\n",
+       "      <td>5975716542231801351</td>\n",
+       "      <td>7000000000000000002</td>\n",
+       "      <td>1724716800</td>\n",
+       "      <td>[12470403414325965877, 3929303517455492411]</td>\n",
+       "      <td>Will Ethan Holliday be drafted in the 2025 MLB...</td>\n",
+       "      <td>1724320709</td>\n",
        "      <td>True</td>\n",
-       "      <td>9</td>\n",
+       "      <td>4</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>Yes</td>\n",
        "      <td>No</td>\n",
-       "      <td>2024-08-21 15:55:30</td>\n",
-       "      <td>28.84</td>\n",
-       "      <td>71.16</td>\n",
-       "      <td>0.569889</td>\n",
-       "      <td>5.129</td>\n",
-       "      <td>8.56</td>\n",
-       "      <td>91.44</td>\n",
+       "      <td>2024-08-22 11:58:29</td>\n",
+       "      <td>23.96</td>\n",
+       "      <td>76.04</td>\n",
+       "      <td>1.395750</td>\n",
+       "      <td>5.583</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>100.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>100.00</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -190,64 +190,64 @@
       "text/plain": [
        "  creationTimestamp                                          id  \\\n",
        "0        1724201135  0x241d212b45ae3ecb2809421df1f3cff2bb2988f0   \n",
-       "1        1724199465  0x320f9768e0fe0d328a9a2c8464f12959b16e5194   \n",
-       "2        1724155795  0x34accb10e7034a8de32bacd17fe56eff48286673   \n",
-       "3        1724199065  0x443248919f03c00d497f84d533545d2a498d6b85   \n",
-       "4        1724154665  0x4aad7221a6d8dd3b9c596446d2d079276befe3da   \n",
+       "1        1724286555  0x2ed5a1a207b1e9b1c17a1c2baf64647c3db9d1f6   \n",
+       "2        1724199465  0x320f9768e0fe0d328a9a2c8464f12959b16e5194   \n",
+       "3        1724287075  0x3c4a1acefa3049f6de2b212fa3141f46b0b5823f   \n",
+       "4        1724285320  0x3fc60512d8fff2a565155ee05aef0d2a79fcec23   \n",
        "\n",
        "      liquidityMeasure   liquidityParameter openingTimestamp  \\\n",
-       "0  6851416565110943855  7000000000000000005       1724630400   \n",
-       "1  5879350969765507881  7000000000000000002       1724630400   \n",
-       "2  6390071369907879264  7000000000000000003       1724371200   \n",
-       "3  6953917419955440631  7000000000000000001       1724630400   \n",
-       "4  6342175206935951613  7000000000000000003       1724457600   \n",
+       "0  6861664707883062434  7000000000000000008       1724630400   \n",
+       "1  6764194343046296637  7000000000000000001       1724716800   \n",
+       "2  5657370332642200804  7000000000000000003       1724630400   \n",
+       "3  6755535026140294583  7000000000000000001       1724716800   \n",
+       "4  5975716542231801351  7000000000000000002       1724716800   \n",
        "\n",
        "                           outcomeTokenAmounts  \\\n",
-       "0   [5686089254551548648, 8617522132769359689]   \n",
-       "1  [3811004712840132698, 12857501811768421751]   \n",
-       "2  [4537576918801928698, 10798715013945731768]   \n",
-       "3   [7853595072000897778, 6239180852943572619]   \n",
-       "4  [10995908979010407929, 4456202765367908944]   \n",
+       "0   [5728447658624505774, 8553800771178854358]   \n",
+       "1   [9108406198169923801, 5379645893465440960]   \n",
+       "2  [3560526624520056083, 13762009154082647147]   \n",
+       "3   [5353172588127988920, 9153450443325863452]   \n",
+       "4  [12470403414325965877, 3929303517455492411]   \n",
        "\n",
        "                                               title  sample_timestamp  open  \\\n",
-       "0  Will SpaceX successfully send four people on a...        1724248530  True   \n",
-       "1  Will the World War II-era bomb in Northern Ire...        1724248530  True   \n",
-       "2  Will James Anderson retire from his cricket ca...        1724248530  True   \n",
-       "3  Will the Texas jury decide the liability of th...        1724248530  True   \n",
-       "4  Will Ukraine launch another strike inside Russ...        1724248530  True   \n",
+       "0  Will SpaceX successfully send four people on a...        1724320709  True   \n",
+       "1  Will there be a significant increase in the pu...        1724320709  True   \n",
+       "2  Will the World War II-era bomb in Northern Ire...        1724320709  True   \n",
+       "3  Will the human remains found on the Michigan m...        1724320709  True   \n",
+       "4  Will Ethan Holliday be drafted in the 2025 MLB...        1724320709  True   \n",
        "\n",
-       "   total_trades  ...  votes_second_outcome_perc  first_outcome  \\\n",
-       "0            14  ...                        0.0            Yes   \n",
-       "1             5  ...                        0.0            Yes   \n",
-       "2             9  ...                        0.0            Yes   \n",
-       "3             2  ...                        0.0            Yes   \n",
-       "4             9  ...                        0.0            Yes   \n",
+       "   total_trades  ...  second_outcome     sample_datetime first_token_perc  \\\n",
+       "0            25  ...              No 2024-08-22 11:58:29            59.89   \n",
+       "1             6  ...              No 2024-08-22 11:58:29            37.13   \n",
+       "2             6  ...              No 2024-08-22 11:58:29            79.45   \n",
+       "3             4  ...              No 2024-08-22 11:58:29            63.10   \n",
+       "4             4  ...              No 2024-08-22 11:58:29            23.96   \n",
        "\n",
-       "   second_outcome     sample_datetime first_token_perc second_token_perc  \\\n",
-       "0              No 2024-08-21 15:55:30            60.25             39.75   \n",
-       "1              No 2024-08-21 15:55:30            77.14             22.86   \n",
-       "2              No 2024-08-21 15:55:30            70.41             29.59   \n",
-       "3              No 2024-08-21 15:55:30            44.27             55.73   \n",
-       "4              No 2024-08-21 15:55:30            28.84             71.16   \n",
+       "  second_token_perc  mean_trade_size  total_bet_amount  \\\n",
+       "0             40.11         0.398600             9.965   \n",
+       "1             62.87         0.411333             2.468   \n",
+       "2             20.55         1.150000             6.900   \n",
+       "3             36.90         0.628500             2.514   \n",
+       "4             76.04         1.395750             5.583   \n",
        "\n",
-       "   mean_trade_size  total_bet_amount  price_weighted_first_outcome_perc  \\\n",
-       "0         0.374714             5.246                              67.42   \n",
-       "1         1.195400             5.977                             100.00   \n",
-       "2         0.739667             6.657                              86.01   \n",
-       "3         1.374000             2.748                              36.39   \n",
-       "4         0.569889             5.129                               8.56   \n",
+       "   price_weighted_first_outcome_perc  price_weighted_second_outcome_perc  \\\n",
+       "0                              62.67                               37.33   \n",
+       "1                               6.48                               93.52   \n",
+       "2                             100.00                                0.00   \n",
+       "3                              93.64                                6.36   \n",
+       "4                               0.00                              100.00   \n",
        "\n",
-       "   price_weighted_second_outcome_perc  \n",
-       "0                               32.58  \n",
-       "1                                0.00  \n",
-       "2                               13.99  \n",
-       "3                               63.61  \n",
-       "4                               91.44  \n",
+       "   bought_tokens_first_perc  bought_tokens_second_perc  \n",
+       "0                     57.34                      42.66  \n",
+       "1                      7.13                      92.87  \n",
+       "2                    100.00                       0.00  \n",
+       "3                     92.98                       7.02  \n",
+       "4                      0.00                     100.00  \n",
        "\n",
        "[5 rows x 22 columns]"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -259,7 +259,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
@@ -276,8 +276,6 @@
        "open                                  0\n",
        "total_trades                          0\n",
        "dist_gap_perc                         0\n",
-       "votes_first_outcome_perc              0\n",
-       "votes_second_outcome_perc             0\n",
        "first_outcome                         0\n",
        "second_outcome                        0\n",
        "sample_datetime                       0\n",
@@ -287,10 +285,12 @@
        "total_bet_amount                      0\n",
        "price_weighted_first_outcome_perc     0\n",
        "price_weighted_second_outcome_perc    0\n",
+       "bought_tokens_first_perc              0\n",
+       "bought_tokens_second_perc             0\n",
        "dtype: int64"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 33,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -301,7 +301,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
    "metadata": {},
    "outputs": [
     {
@@ -309,34 +316,34 @@
      "output_type": "stream",
      "text": [
       "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 82 entries, 0 to 81\n",
+      "RangeIndex: 41 entries, 0 to 40\n",
       "Data columns (total 22 columns):\n",
       " #   Column                              Non-Null Count  Dtype         \n",
       "---  ------                              --------------  -----         \n",
-      " 0   creationTimestamp                   82 non-null     object        \n",
-      " 1   id                                  82 non-null     object        \n",
-      " 2   liquidityMeasure                    82 non-null     int64         \n",
-      " 3   liquidityParameter                  82 non-null     object        \n",
-      " 4   openingTimestamp                    82 non-null     object        \n",
-      " 5   outcomeTokenAmounts                 82 non-null     object        \n",
-      " 6   title                               82 non-null     object        \n",
-      " 7   sample_timestamp                    82 non-null     int64         \n",
-      " 8   open                                82 non-null     bool          \n",
-      " 9   total_trades                        82 non-null     int64         \n",
-      " 10  dist_gap_perc                       82 non-null     float64       \n",
-      " 11  votes_first_outcome_perc            82 non-null     float64       \n",
-      " 12  votes_second_outcome_perc           82 non-null     float64       \n",
-      " 13  first_outcome                       82 non-null     object        \n",
-      " 14  second_outcome                      82 non-null     object        \n",
-      " 15  sample_datetime                     82 non-null     datetime64[ns]\n",
-      " 16  first_token_perc                    82 non-null     float64       \n",
-      " 17  second_token_perc                   82 non-null     float64       \n",
-      " 18  mean_trade_size                     82 non-null     float64       \n",
-      " 19  total_bet_amount                    82 non-null     float64       \n",
-      " 20  price_weighted_first_outcome_perc   82 non-null     float64       \n",
-      " 21  price_weighted_second_outcome_perc  82 non-null     float64       \n",
+      " 0   creationTimestamp                   41 non-null     object        \n",
+      " 1   id                                  41 non-null     object        \n",
+      " 2   liquidityMeasure                    41 non-null     int64         \n",
+      " 3   liquidityParameter                  41 non-null     object        \n",
+      " 4   openingTimestamp                    41 non-null     object        \n",
+      " 5   outcomeTokenAmounts                 41 non-null     object        \n",
+      " 6   title                               41 non-null     object        \n",
+      " 7   sample_timestamp                    41 non-null     int64         \n",
+      " 8   open                                41 non-null     bool          \n",
+      " 9   total_trades                        41 non-null     int64         \n",
+      " 10  dist_gap_perc                       41 non-null     float64       \n",
+      " 11  first_outcome                       41 non-null     object        \n",
+      " 12  second_outcome                      41 non-null     object        \n",
+      " 13  sample_datetime                     41 non-null     datetime64[ns]\n",
+      " 14  first_token_perc                    41 non-null     float64       \n",
+      " 15  second_token_perc                   41 non-null     float64       \n",
+      " 16  mean_trade_size                     41 non-null     float64       \n",
+      " 17  total_bet_amount                    41 non-null     float64       \n",
+      " 18  price_weighted_first_outcome_perc   41 non-null     float64       \n",
+      " 19  price_weighted_second_outcome_perc  41 non-null     float64       \n",
+      " 20  bought_tokens_first_perc            41 non-null     float64       \n",
+      " 21  bought_tokens_second_perc           41 non-null     float64       \n",
       "dtypes: bool(1), datetime64[ns](1), float64(9), int64(3), object(8)\n",
-      "memory usage: 13.7+ KB\n"
+      "memory usage: 6.9+ KB\n"
      ]
     }
    ],
@@ -346,19 +353,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "sample_timestamp\n",
-       "1724248530    41\n",
-       "1724253161    41\n",
+       "1724320709    41\n",
        "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 35,
      "metadata": {},
      "output_type": "execute_result"
     }

tabs/dist_gap.py

@@ -34,6 +34,33 @@ def get_dist_gap_time_evolution(market_id: str, all_markets: pd.DataFrame):
     )
 
 
+def get_avg_gap_time_evolution(all_markets: pd.DataFrame):
+    avg_dist_gap_perc = (
+        all_markets.groupby("sample_datetime")["dist_gap_perc"].mean().reset_index()
+    )
+    avg_dist_gap_perc["sample_datetime"] = avg_dist_gap_perc["sample_datetime"].astype(
+        str
+    )
+    avg_dist_gap_perc.rename(
+        columns={"dist_gap_perc": "mean_dist_gap_perc"}, inplace=True
+    )
+    avg_dist_gap_perc.columns = avg_dist_gap_perc.columns.astype(str)
+    return gr.LinePlot(
+        value=avg_dist_gap_perc,
+        x="sample_datetime",
+        y="mean_dist_gap_perc",
+        y_title="Mean dist gap percentage (%)",
+        interactive=True,
+        show_actions_button=True,
+        tooltip=[
+            "sample_datetime",
+            "mean_dist_gap_perc",
+        ],
+        height=HEIGHT,
+        width=WIDTH,
+    )
+
+
 def get_top_best_behaviour_markets(markets_data: pd.DataFrame):
     """Function to paint the top markets with the lowest metric of distribution gap"""
     sorted_data = markets_data.sort_values(by="dist_gap_perc", ascending=False)