itsderek23 · July 10, 2019 19:15 · Jul 10, 2019
diff --git a/impression_outliers_print.py b/impression_outliers_print.py
@@ -0,0 +1,19 @@
+from sklearn.ensemble import IsolationForest
+
+def print_anomalies(query,column):
+    df_anom = df[(df['query'] == query) & (df['device'] == 'desktop')]
+    x=df_anom[column].values
+    xx = np.linspace(df_anom[column].min(), df_anom[column].max(), len(df)).reshape(-1,1)
+
+    isolation_forest = IsolationForest(n_estimators=100)
+    isolation_forest.fit(x.reshape(-1, 1))
+
+    anomaly_score = isolation_forest.decision_function(xx)
+    # 1 = inlier, 0 = outlier
+    outlier = isolation_forest.predict(xx)
+    df_outliers = df_anom[list(map(lambda v: True if v < 0 else False,isolation_forest.predict(x.reshape(-1, 1))))]
+    df_outliers = df_outliers[df_outliers.date >= df.date.max() - datetime.timedelta(days=14)] 
+    print(df_outliers)
+
+for q in top_queries_by_clicks:
+    print_anomalies(q,'impressions')