updating scripts

scripts/closed_markets_divergence.py

@@ -1,6 +1,4 @@
-from pathlib import Path
 import os
-import math
 import pandas as pd
 import numpy as np
 from typing import Any, Union
@@ -11,6 +9,7 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 from tqdm import tqdm
 import time
 from datetime import datetime
+from utils import DATA_DIR, TMP_DIR
 
 NUM_WORKERS = 10
 IPFS_POLL_INTERVAL = 0.2
@@ -18,9 +17,6 @@ INVALID_ANSWER_HEX = (
     "0xffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff"
 )
 INVALID_ANSWER = -1
-SCRIPTS_DIR = Path(__file__).parent
-ROOT_DIR = SCRIPTS_DIR.parent
-DATA_DIR = ROOT_DIR / "data"
 SUBGRAPH_API_KEY = os.environ.get("SUBGRAPH_API_KEY", None)
 OMEN_SUBGRAPH_URL = Template(
     """https://gateway-arbitrum.network.thegraph.com/api/${subgraph_api_key}/subgraphs/id/9fUVQpFwzpdWS9bq5WkAnmKbNNcoBwatMR4yZq81pbbz"""
@@ -105,7 +101,7 @@ def convert_hex_to_int(x: Union[str, float]) -> Union[int, float]:
 def get_closed_markets():
     print("Reading parquet file with closed markets data from trades")
     try:
-        markets = pd.read_parquet(DATA_DIR / "fpmmTrades.parquet")
+        markets = pd.read_parquet(TMP_DIR / "fpmmTrades.parquet")
     except Exception:
         print("Error reading the parquet file")
 

scripts/metrics.py

@@ -252,21 +252,30 @@ def compute_daily_metrics_by_market_creator(
 
 
 def compute_winning_metrics_by_trader(
-    traders_data: pd.DataFrame, trader_filter: str = None
+    traders_data: pd.DataFrame, unknown_info: pd.DataFrame, trader_filter: str = None
 ) -> pd.DataFrame:
     """Function to compute the winning metrics at the trader level per week and with different market creators"""
-    market_all = traders_data.copy(deep=True)
+    if len(unknown_info) > 0:
+        all_data = pd.concat([traders_data, unknown_info], axis=0)
+    else:
+        all_data = traders_data
+
+    market_all = all_data.copy(deep=True)
     market_all["market_creator"] = "all"
 
     # merging both dataframes
-    final_traders = pd.concat([market_all, traders_data], ignore_index=True)
+    final_traders = pd.concat([market_all, all_data], ignore_index=True)
     final_traders = final_traders.sort_values(by="creation_timestamp", ascending=True)
 
-    if trader_filter == "Olas":
-        final_traders = final_traders.loc[final_traders["staking"] != "non_Olas"]
-    else:  # non_Olas traders
+    if trader_filter == "non_Olas":  # non_Olas
         final_traders = final_traders.loc[final_traders["staking"] == "non_Olas"]
+    elif trader_filter == "Olas":
+        final_traders = final_traders.loc[final_traders["staking"] != "non_Olas"]
+    else:  # all traders
+        print("No filtering")
 
+    if len(final_traders) == 0:
+        return pd.DataFrame()
     winning_df = win_metrics_trader_level(final_traders)
     winning_df.head()
     return winning_df

scripts/num_mech_calls.py

@@ -69,7 +69,7 @@ def compute_total_mech_calls():
         print(f"Error updating the invalid trades parquet {e}")
 
     print("Reading trades weekly info file")
-    fpmmTrades = pd.read_parquet(DATA_DIR / "fpmmTrades.parquet")
+    fpmmTrades = pd.read_parquet(TMP_DIR / "fpmmTrades.parquet")
     try:
         fpmmTrades["creationTimestamp"] = fpmmTrades["creationTimestamp"].apply(
             lambda x: transform_to_datetime(x)

scripts/retention_metrics.py

@@ -106,6 +106,8 @@ def calculate_cohort_retention(
     df_filtered = df.loc[
         (df["market_creator"] == market_creator) & (df["trader_type"] == trader_type)
     ]
+    if len(df_filtered) == 0:
+        return pd.DataFrame()
     df_filtered = df_filtered.sort_values(by="creation_timestamp", ascending=True)
     # Get first week of activity for each trader
     first_activity = (