fix typo

app.py

@@ -5,7 +5,10 @@ import pandas as pd
 import seaborn as sns
 import duckdb
 import logging
-from tabs.tokens_votes_dist import get_based_tokens_distribution
+from tabs.tokens_votes_dist import (
+    get_based_tokens_distribution,
+    get_based_votes_distribution,
+)
 
 
 def get_logger():
@@ -48,10 +51,10 @@ def get_extreme_cases(live_fpmms: pd.DataFrame):
     """Function to return the id of the best and worst case according to the dist gap metric"""
     # select markets with more than 1 sample
     samples_per_market = (
-        live_fpmms[["id", "tokens_timestamp"]].groupby("id").count().reset_index()
+        live_fpmms[["id", "sample_timestamp"]].groupby("id").count().reset_index()
     )
     markets_with_multiple_samples = list(
-        samples_per_market.loc[samples_per_market["tokens_timestamp"] > 1, "id"].values
+        samples_per_market.loc[samples_per_market["sample_timestamp"] > 1, "id"].values
     )
     selected_markets = live_fpmms.loc[
         live_fpmms["id"].isin(markets_with_multiple_samples)
@@ -74,6 +77,7 @@ with demo:
 
             with gr.Row():
                 gr.Markdown("Best case: a market with a low distribution gap metric")
+                gr.Markdown(f"Market id = {best_market_id}")
             with gr.Row():
                 best_market_tokens_dist = get_based_tokens_distribution(
                     best_market_id, markets_data
@@ -81,6 +85,7 @@ with demo:
 
             with gr.Row():
                 gr.Markdown("Worst case: a market with a high distribution gap metric")
+                gr.Markdown(f"Market id = {worst_market_id}")
 
             with gr.Row():
                 worst_market_tokens_dist = get_based_tokens_distribution(

tabs/tokens_votes_dist.py

@@ -32,3 +32,31 @@ def get_based_tokens_distribution(market_id: str, all_markets: pd.DataFrame):
         labels=[first_outcome, second_outcome],
     )
     return gr.Plot(value=ax.figure)
+
+
+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"""
+    selected_market = all_markets.loc[all_markets["id"] == market_id]
+    ax = selected_market.plot(
+        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=16
+    )
+
+    # add axis titles
+    plt.xlabel("Sample date")
+    plt.ylabel("Percentage")
+    first_outcome = selected_market.iloc[0].first_outcome
+    second_outcome = selected_market.iloc[0].second_outcome
+    ax.legend(
+        bbox_to_anchor=(1, 1.02),
+        loc="upper left",
+        labels=[first_outcome, second_outcome],
+    )
+    return gr.Plot(value=ax.figure)