anomaly-pipeline 0.1.27__py3-none-any.whl

anomaly_pipeline/helpers/fb_prophet.py

@@ -0,0 +1,94 @@
+import pandas as pd
+import logging
+import numpy as np
+from prophet import Prophet
+import warnings
+import os
+import sys
+from contextlib import contextmanager
+
+warnings.filterwarnings("ignore")
+
+# --- ADD THIS HELPER ---
+@contextmanager
+def suppress_stdout_stderr():
+    """Redirects stdout and stderr to devnull to silence C++ logs."""
+    with open(os.devnull, 'w') as fnull:
+        old_stdout, old_stderr = sys.stdout, sys.stderr
+        sys.stdout, sys.stderr = fnull, fnull
+        try:
+            yield
+        finally:
+            sys.stdout, sys.stderr = old_stdout, old_stderr
+
+def detect_time_series_anomalies_fb_walkforward(
+    group,
+    variable,
+    date_column,
+    eval_period,
+    interval_width
+):
+    # 1. Silence the cmdstanpy logger completely
+    logger = logging.getLogger('cmdstanpy')
+    logger.addHandler(logging.NullHandler())
+    logger.propagate = False
+    logger.setLevel(logging.CRITICAL) # Only show critical errors
+    
+    group = group.sort_values(date_column).copy()
+    group[date_column] = pd.to_datetime(group[date_column])
+
+    cutoff_date = group[date_column].max() - pd.Timedelta(weeks=eval_period)
+
+    group["FB_forecast"] = np.nan
+    group["FB_low"] = np.nan
+    group["FB_high"] = np.nan
+
+    train = group[group[date_column] <= cutoff_date].copy()
+    test = group[group[date_column] > cutoff_date].copy()
+
+    for i, row in test.iterrows():
+        prophet_train = train.rename(columns={date_column: "ds", variable: "y"})
+
+        try:
+            model = Prophet(
+                weekly_seasonality=True,
+                yearly_seasonality=True,
+                daily_seasonality=False,
+                interval_width=interval_width
+            )
+            
+            # --- WRAP THE FIT IN THE MUTER ---
+            with suppress_stdout_stderr():
+                model.fit(prophet_train)
+
+            future = pd.DataFrame({"ds": [row[date_column]]})
+            fc = model.predict(future).iloc[0]
+
+            group.loc[i, "FB_forecast"] = fc["yhat"]
+            group.loc[i, "FB_low"] = max(fc["yhat_lower"], 0)
+            group.loc[i, "FB_high"] = fc["yhat_upper"]
+
+        except Exception as e:
+            # Note: We don't mute this so you can still see actual errors
+            print(f"Prophet failed for KEY={group['key'].iloc[0]} on date={row[date_column]}: {e}")
+            group.loc[i, "FB_forecast"] = train[variable].iloc[-1]
+            group.loc[i, "FB_low"] = max(train[variable].iloc[-1], 0)
+            group.loc[i, "FB_high"] = train[variable].iloc[-1]
+
+        new_train_row = row.to_frame().T
+        train = pd.concat([train, new_train_row], ignore_index=True)
+
+    group["FB_residual"] = group[variable] - group["FB_forecast"]
+    group["FB_anomaly"] = np.nan
+    mask = group[date_column] > cutoff_date
+
+    group.loc[mask & (group[variable] > group["FB_high"]), "FB_anomaly"] = "high"
+    group.loc[mask & (group[variable] < group["FB_low"]), "FB_anomaly"] = "low"
+
+    group["is_FB_anomaly"] = group["FB_anomaly"].notna()
+    
+    train_mask = group[date_column] <= cutoff_date
+    group.loc[train_mask, "FB_residual"] = np.nan
+    group.loc[train_mask, "is_FB_anomaly"] = np.nan
+
+    return group