feat: add time filter

server/app.py

@@ -55,19 +55,6 @@ def word_frequencies():
         print(traceback.format_exc())
         return jsonify({"error": f"An unexpected error occurred: {str(e)}"}), 500
     
-@app.route('/stats/search', methods=["POST"])
-def search_dataset():
-    if stat_obj is None:
-        return jsonify({"error": "No data uploaded"}), 400
-
-    data = request.get_json(silent=True) or {}
-
-    if "query" not in data:
-        return stat_obj.df
-    
-    query = data["query"]
-    return jsonify(stat_obj.filter_events(query).to_dict(orient='records')), 200
-
 @app.route('/stats/summary', methods=["GET"])
 def get_summary():
     if stat_obj is None:
@@ -93,7 +80,44 @@ def get_time_analysis():
         print(traceback.format_exc())
         return jsonify({"error": f"An unexpected error occurred: {str(e)}"}), 500
     
-@app.route('/reset', methods=["GET"])
+@app.route('/filter/search', methods=["POST"])
+def search_dataset():
+    if stat_obj is None:
+        return jsonify({"error": "No data uploaded"}), 400
+
+    data = request.get_json(silent=True) or {}
+
+    if "query" not in data:
+        return stat_obj.df
+    
+    query = data["query"]
+    filtered_df = stat_obj.search(query)
+
+    return jsonify(filtered_df), 200
+
+@app.route('/filter/time', methods=["POST"])
+def filter_time():
+    if stat_obj is None:
+        return jsonify({"error": "No data uploaded"}), 400
+    
+    data = request.get_json(silent=True)
+    if not data:
+        return jsonify({"error": "Invalid or missing JSON body"}), 400
+
+    if "start" not in data or "end" not in data:
+        return jsonify({"error": "Please include both start and end dates"}), 400
+    
+    try:
+        start = pd.to_datetime(data["start"], utc=True)
+        end = pd.to_datetime(data["end"], utc=True)
+    except Exception:
+        return jsonify({"error": "Invalid datetime format"}), 400
+
+    filtered_df = stat_obj.set_time_range(start, end)
+
+    return jsonify(filtered_df), 200
+    
+@app.route('/filter/reset', methods=["GET"])
 def reset_dataset():
     if stat_obj is None:
         return jsonify({"error": "No data uploaded"}), 400

server/stat_gen.py

@@ -1,6 +1,7 @@
 import pandas as pd
 import re
 import nltk
+import datetime
 
 from nltk.corpus import stopwords
 from collections import Counter
@@ -27,9 +28,10 @@ class StatGen:
         comments_df["parent_id"] = comments_df.get("post_id")
 
         self.df = pd.concat([posts_df, comments_df])
-        self.original_df = self.df.copy(deep=True)
         self._add_date_cols(self.df)
 
+        self.original_df = self.df.copy(deep=True)
+
     ## Private Methods
     def _add_date_cols(self, df: pd.DataFrame) -> None:
         df['date'] = pd.to_datetime(df['timestamp'], unit='s').dt.date
@@ -123,9 +125,26 @@ class StatGen:
             "word_frequencies": word_frequencies.to_dict(orient='records')
         }
     
-    def filter_events(self, search_query: str) -> pd.DataFrame:
-        self.df = self.df[self.df["content"].str.contains(search_query)]
-        return self.df
+    def search(self, search_query: str) -> pd.DataFrame:
+        self.df = self.df[
+            self.df["content"].str.contains(search_query)
+        ]
+
+        return {
+            "rows": len(self.df),
+            "data": self.df.to_dict(orient="records")
+        }
+    
+    def set_time_range(self, start: datetime.datetime, end: datetime.datetime):
+        self.df = self.df[
+            (self.df["dt"] >= start) &
+            (self.df["dt"] <= end)
+        ]
+
+        return {
+            "rows": len(self.df),
+            "data": self.df.to_dict(orient="records")
+        }
     
     def reset_dataset(self) -> None:
         self.df = self.original_df.copy(deep=True)