DAA graphs based on Dune data

app.py

@@ -33,7 +33,7 @@ from tabs.daily_graphs import (
     plot_daily_metrics,
     trader_daily_metric_choices,
     default_daily_metric,
-    plot_rolling_average,
+    plot_rolling_average_dune,
 )
 from scripts.utils import get_traders_family
 from tabs.market_plots import (
@@ -137,14 +137,21 @@ def load_all_data():
     )
     df7 = pd.read_parquet(all_mech_calls_df)
 
-    # gnosis_txs_dataset.parquet
-    gnosis_txs_df = hf_hub_download(
+    # daa for quickstart and pearl
+    daa_qs_df = hf_hub_download(
         repo_id="valory/Olas-predict-dataset",
-        filename="gnosis_txs_dataset.parquet",
+        filename="latest_result_DAA_QS.parquet",
         repo_type="dataset",
     )
-    df8 = pd.read_parquet(gnosis_txs_df)
-    return df1, df2, df3, df4, df5, df6, df7, df8
+    df8 = pd.read_parquet(daa_qs_df)
+
+    daa_pearl_df = hf_hub_download(
+        repo_id="valory/Olas-predict-dataset",
+        filename="latest_result_DAA_Pearl.parquet",
+        repo_type="dataset",
+    )
+    df9 = pd.read_parquet(daa_pearl_df)
+    return df1, df2, df3, df4, df5, df6, df7, df8, df9
 
 
 def prepare_data():
@@ -157,7 +164,8 @@ def prepare_data():
         retention_df,
         active_traders,
         all_mech_calls,
-        gnosis_txs_df,
+        daa_qs_df,
+        daa_pearl_df,
     ) = load_all_data()
     all_trades["creation_timestamp"] = all_trades["creation_timestamp"].dt.tz_convert(
         "UTC"
@@ -204,40 +212,27 @@ def prepare_data():
         .dt.start_time.dt.strftime("%b-%d-%Y")
     )
 
-    # prepare daa dataset concatenating all_trades and gnosis_txs_df
-    selected_trades = all_trades[all_trades["staking"] != "non_Olas"].copy(deep=True)
-    selected_trades = selected_trades[
-        [
-            "market_creator",
-            "trader_address",
-            "creation_timestamp",
-        ]
-    ]
-    selected_trades.drop_duplicates(inplace=True)
-    selected_trades["tx_date"] = pd.to_datetime(
-        selected_trades["creation_timestamp"].dt.date, format="%b-%d-%Y"
+    # prepare the daa dataframes
+    daa_pearl_df["day"] = pd.to_datetime(
+        daa_pearl_df["day"], format="%Y-%m-%d 00:00:00.000 UTC"
     )
-
-    gnosis_txs_df["tx_date"] = pd.to_datetime(gnosis_txs_df["tx_datetime"]).dt.date
-    gnosis_txs_df = gnosis_txs_df[
-        [
-            "trader_address",
-            "tx_date",
-            "market_creator",
-        ]
-    ]
-    gnosis_txs_df["tx_date"] = pd.to_datetime(
-        gnosis_txs_df["tx_date"], format="%b-%d-%Y"
+    daa_qs_df["day"] = pd.to_datetime(
+        daa_qs_df["day"], format="%Y-%m-%d 00:00:00.000 UTC"
+    )
+    daa_pearl_df["day"] = daa_pearl_df["day"].dt.tz_localize("UTC")
+    daa_qs_df["day"] = daa_qs_df["day"].dt.tz_localize("UTC")
+    daa_qs_df["tx_date"] = pd.to_datetime(daa_qs_df["day"]).dt.date
+    daa_pearl_df["tx_date"] = pd.to_datetime(daa_pearl_df["day"]).dt.date
+    daa_pearl_df["seven_day_trailing_avg"] = pd.to_numeric(
+        daa_pearl_df["seven_day_trailing_avg"], errors="coerce"
     )
-    selected_trades = selected_trades[
-        [
-            "trader_address",
-            "tx_date",
-            "market_creator",
-        ]
-    ]
-    daa_df = pd.concat([selected_trades, gnosis_txs_df], ignore_index=True)
-    daa_df.drop_duplicates(inplace=True)
+    daa_pearl_df["seven_day_trailing_avg"] = daa_pearl_df[
+        "seven_day_trailing_avg"
+    ].round(2)
+    daa_qs_df["seven_day_trailing_avg"] = pd.to_numeric(
+        daa_qs_df["seven_day_trailing_avg"], errors="coerce"
+    )
+    daa_qs_df["seven_day_trailing_avg"] = daa_qs_df["seven_day_trailing_avg"].round(2)
     return (
         traders_data,
         closed_markets,
@@ -246,7 +241,8 @@ def prepare_data():
         retention_df,
         active_traders,
         all_mech_calls,
-        daa_df,
+        daa_qs_df,
+        daa_pearl_df,
     )
 
 
@@ -258,7 +254,8 @@ def prepare_data():
     raw_retention_df,
     active_traders,
     all_mech_calls,
-    daa_df,
+    daa_qs_df,
+    daa_pearl_df,
 ) = prepare_data()
 
 retention_df = prepare_retention_dataset(
@@ -690,16 +687,14 @@ with demo:
             with gr.Row():
                 gr.Markdown(" # Daily active agents in Pearl markets")
             with gr.Row():
-                rolling_avg_plot = plot_rolling_average(
-                    daa_df,
-                    market_creator="pearl",
+                rolling_avg_plot = plot_rolling_average_dune(
+                    daa_pearl_df,
                 )
             with gr.Row():
                 gr.Markdown(" # Daily active agents in QS markets")
             with gr.Row():
-                rolling_avg_plot = plot_rolling_average(
-                    daa_df,
-                    market_creator="quickstart",
+                rolling_avg_plot = plot_rolling_average_dune(
+                    daa_qs_df,
                 )
 
         with gr.TabItem("📉 Markets Kullback–Leibler divergence"):

tabs/daily_graphs.py

@@ -265,7 +265,7 @@ def plot_rolling_average(
     print(rolling_avg_df.head())
 
     # Ensure 'creation_date' is a column, not an index
-    if "creation_date" not in rolling_avg_df.columns:
+    if "tx_date" not in rolling_avg_df.columns:
         rolling_avg_df = rolling_avg_df.reset_index()
 
     fig = px.bar(
@@ -281,3 +281,23 @@ def plot_rolling_average(
     return gr.Plot(
         value=fig,
     )
+
+
+def plot_rolling_average_dune(
+    daa_df: pd.DataFrame,
+) -> gr.Plot:
+    """Function to plot the rolling average of daily active traders"""
+
+    fig = px.bar(
+        daa_df,
+        x="tx_date",
+        y="seven_day_trailing_avg",
+    )
+    fig.update_layout(
+        xaxis_title="Date",
+        yaxis_title="7-day rolling average of DAA",
+    )
+
+    return gr.Plot(
+        value=fig,
+    )