gap decimals and filter of trades

app.py

@@ -60,7 +60,8 @@ def prepare_data():
 demo = gr.Blocks()
 markets_data = prepare_data()
 live_markets_data = markets_data.loc[markets_data["open"] == True]
-
+# filter only those with trades
+markets_data = markets_data.loc[markets_data["total_trades"] > 0]
 with demo:
     gr.HTML("<h1>Olas Predict Live Markets </h1>")
     gr.Markdown("This app shows the distributions of predictions on the live markets.")
@@ -72,7 +73,9 @@ with demo:
             with gr.Row():
                 gr.Markdown("Best case: a market with a low gap between distributions")
             with gr.Row():
-                gr.Markdown(f"Market id = {best_market_id} Dist gap = {best_gap}")
+                gr.Markdown(
+                    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")
@@ -88,7 +91,9 @@ with demo:
             with gr.Row():
                 gr.Markdown("Worst case: a market with a high distribution gap metric")
             with gr.Row():
-                gr.Markdown(f"Market id = {worst_market_id} Dist gap = {worst_gap}")
+                gr.Markdown(
+                    f"Market id = {worst_market_id} Dist gap = {round(worst_gap,2)}"
+                )
 
             with gr.Row():
                 with gr.Column(min_width=350):
@@ -102,6 +107,7 @@ with demo:
                     )
 
         with gr.TabItem("📏 Distribution gap metric"):
+            # remove samples with no trades
             with gr.Row():
                 gr.Markdown(
                     "This metric measures the difference between the probability distribution based on the tokens distribution and the one based on the votes distribution"

notebooks/research_on_specific_markets.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -225,7 +225,7 @@
        "4              50.32              NaN 2024-07-31 18:06:59  "
       ]
      },
-     "execution_count": 8,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -279,16 +279,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
-    "id = \"0xf2db83c7a5f926290fb93cebea810746cd674916\""
+    "id = \"0xfc417a9bc90f15eb65f30368f5794e7b39f93e76\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -297,7 +297,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -344,48 +344,48 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>122</th>\n",
-       "      <td>1722571590</td>\n",
-       "      <td>0xf2db83c7a5f926290fb93cebea810746cd674916</td>\n",
-       "      <td>7000000000000000000</td>\n",
-       "      <td>7000000000000000000</td>\n",
+       "      <th>124</th>\n",
+       "      <td>1722563105</td>\n",
+       "      <td>0xfc417a9bc90f15eb65f30368f5794e7b39f93e76</td>\n",
+       "      <td>6999779315564848653</td>\n",
+       "      <td>7000000000000000001</td>\n",
        "      <td>1722988800</td>\n",
-       "      <td>[7000000000000000000, 7000000000000000000]</td>\n",
-       "      <td>Will Donald Trump's campaign announce another ...</td>\n",
+       "      <td>[7055806015023361612, 6944635367762128326]</td>\n",
+       "      <td>Will the Canadian women's football officials b...</td>\n",
        "      <td>1722593849</td>\n",
        "      <td>True</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.00</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0.40</td>\n",
        "      <td>50.00</td>\n",
        "      <td>50.00</td>\n",
        "      <td>Yes</td>\n",
        "      <td>No</td>\n",
-       "      <td>50.00</td>\n",
-       "      <td>50.00</td>\n",
-       "      <td>0.000000</td>\n",
+       "      <td>49.60</td>\n",
+       "      <td>50.40</td>\n",
+       "      <td>0.13000</td>\n",
        "      <td>2024-08-02 12:17:29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>166</th>\n",
-       "      <td>1722571590</td>\n",
-       "      <td>0xf2db83c7a5f926290fb93cebea810746cd674916</td>\n",
-       "      <td>6949985446986235988</td>\n",
-       "      <td>7000000000000000011</td>\n",
+       "      <th>167</th>\n",
+       "      <td>1722563105</td>\n",
+       "      <td>0xfc417a9bc90f15eb65f30368f5794e7b39f93e76</td>\n",
+       "      <td>6511633178027486360</td>\n",
+       "      <td>7000000000000000006</td>\n",
        "      <td>1722988800</td>\n",
-       "      <td>[6209077712260007050, 7891671238587987896]</td>\n",
-       "      <td>Will Donald Trump's campaign announce another ...</td>\n",
-       "      <td>1722847693</td>\n",
+       "      <td>[10286430731240040164, 4763557086053793703]</td>\n",
+       "      <td>Will the Canadian women's football officials b...</td>\n",
+       "      <td>1722852594</td>\n",
        "      <td>True</td>\n",
-       "      <td>39</td>\n",
-       "      <td>13.26</td>\n",
-       "      <td>69.23</td>\n",
-       "      <td>30.77</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1.68</td>\n",
+       "      <td>33.33</td>\n",
+       "      <td>66.67</td>\n",
        "      <td>Yes</td>\n",
        "      <td>No</td>\n",
-       "      <td>55.97</td>\n",
-       "      <td>44.03</td>\n",
-       "      <td>0.646436</td>\n",
-       "      <td>NaT</td>\n",
+       "      <td>31.65</td>\n",
+       "      <td>68.35</td>\n",
+       "      <td>0.35881</td>\n",
+       "      <td>2024-08-05 12:09:54</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -393,35 +393,35 @@
       ],
       "text/plain": [
        "    creationTimestamp                                          id  \\\n",
-       "122        1722571590  0xf2db83c7a5f926290fb93cebea810746cd674916   \n",
-       "166        1722571590  0xf2db83c7a5f926290fb93cebea810746cd674916   \n",
+       "124        1722563105  0xfc417a9bc90f15eb65f30368f5794e7b39f93e76   \n",
+       "167        1722563105  0xfc417a9bc90f15eb65f30368f5794e7b39f93e76   \n",
        "\n",
        "        liquidityMeasure   liquidityParameter openingTimestamp  \\\n",
-       "122  7000000000000000000  7000000000000000000       1722988800   \n",
-       "166  6949985446986235988  7000000000000000011       1722988800   \n",
+       "124  6999779315564848653  7000000000000000001       1722988800   \n",
+       "167  6511633178027486360  7000000000000000006       1722988800   \n",
        "\n",
-       "                            outcomeTokenAmounts  \\\n",
-       "122  [7000000000000000000, 7000000000000000000]   \n",
-       "166  [6209077712260007050, 7891671238587987896]   \n",
+       "                             outcomeTokenAmounts  \\\n",
+       "124   [7055806015023361612, 6944635367762128326]   \n",
+       "167  [10286430731240040164, 4763557086053793703]   \n",
        "\n",
        "                                                 title  sample_timestamp  \\\n",
-       "122  Will Donald Trump's campaign announce another ...        1722593849   \n",
-       "166  Will Donald Trump's campaign announce another ...        1722847693   \n",
+       "124  Will the Canadian women's football officials b...        1722593849   \n",
+       "167  Will the Canadian women's football officials b...        1722852594   \n",
        "\n",
        "     open  total_trades  dist_gap_perc  votes_first_outcome_perc  \\\n",
-       "122  True             0           0.00                     50.00   \n",
-       "166  True            39          13.26                     69.23   \n",
+       "124  True             2           0.40                     50.00   \n",
+       "167  True            21           1.68                     33.33   \n",
        "\n",
        "     votes_second_outcome_perc first_outcome second_outcome  first_token_perc  \\\n",
-       "122                      50.00           Yes             No             50.00   \n",
-       "166                      30.77           Yes             No             55.97   \n",
+       "124                      50.00           Yes             No             49.60   \n",
+       "167                      66.67           Yes             No             31.65   \n",
        "\n",
        "     second_token_perc  mean_trade_size     sample_datetime  \n",
-       "122              50.00         0.000000 2024-08-02 12:17:29  \n",
-       "166              44.03         0.646436                 NaT  "
+       "124              50.40          0.13000 2024-08-02 12:17:29  \n",
+       "167              68.35          0.35881 2024-08-05 12:09:54  "
       ]
      },
-     "execution_count": 11,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }

tabs/tokens_votes_dist.py

@@ -12,12 +12,8 @@ def get_based_tokens_distribution(market_id: str, all_markets: pd.DataFrame):
     """Function to paint the evolution of the probability of the outcomes based on the tokens distributions over time"""
     sns.set_style("darkgrid")
     selected_market = all_markets.loc[all_markets["id"] == market_id]
-    ax = selected_market.plot(
-        x="sample_datetime",
-        y=["first_token_perc", "second_token_perc"],
-        kind="bar",
-        rot=0,
-        stacked=True,
+    ax = selected_market.plotbarh(
+        x="sample_datetime", y=["first_token_perc", "second_token_perc"], stacked=True
     )
     # add overall title
     # plt.title(
@@ -25,8 +21,8 @@ def get_based_tokens_distribution(market_id: str, all_markets: pd.DataFrame):
     # )
 
     # add axis titles
-    plt.xlabel("Sample date")
-    plt.ylabel("Percentage")
+    plt.xlabel("Probability percentage(%)")
+    plt.ylabel("Sample date")
     first_outcome = selected_market.iloc[0].first_outcome
     second_outcome = selected_market.iloc[0].second_outcome
     ax.legend(
@@ -40,19 +36,17 @@ def get_based_votes_distribution(market_id: str, all_markets: pd.DataFrame):
     """Function to paint the evolution of the probability of the outcomes based on the votes distributions over time"""
     sns.set_style("darkgrid")
     selected_market = all_markets.loc[all_markets["id"] == market_id]
-    ax = selected_market.plot(
+    ax = selected_market.plot.barh(
         x="sample_datetime",
         y=["votes_first_outcome_perc", "votes_second_outcome_perc"],
-        kind="bar",
-        rot=0,
         stacked=True,
     )
     # add overall title
     # plt.title("Outcomes probability over time based on votes distributions", fontsize=8)
 
     # add axis titles
-    plt.xlabel("Sample date")
-    plt.ylabel("Percentage")
+    plt.xlabel("Probability percentage(%)")
+    plt.ylabel("Sample date")
     first_outcome = selected_market.iloc[0].first_outcome
     second_outcome = selected_market.iloc[0].second_outcome
     ax.legend(