cleanup

app.py

@@ -1,4 +1,3 @@
-import json
 import urllib.request
 from flask import Flask, jsonify, request
 from flask_cors import CORS

data/preprocessing/preprocess_features.py

@@ -4,18 +4,13 @@
 
 
 class PreprocessFeatures:
-    # def __init__(self, df, labels_df):
     def __init__(self, df):
         self.df = df
-        # self.labels_df = labels_df
 
     def get_features_for_model(self):
         self.append_time_features()
         # self.get_lagged_features()
 
-        pd.set_option('display.max_columns', None)
-        print(self.df.head())
-
         return self.df[feature_columns], len(feature_columns)
 
     def append_time_features(self):
@@ -53,7 +48,6 @@ def append_time_features(self):
         self.df['sin_month'] = np.sin(2 * np.pi * self.df['month'] / month_in_year)
         self.df['cos_month'] = np.cos(2 * np.pi * self.df['month'] / month_in_year)
 
-    def get_lagged_features(self, period=24):
-        for label in parking_data_labels:
-            pass
-            # self.df[label + '_lagged_' + str(period)] = self.labels_df[label].shift(periods=period)
+    # def get_lagged_features(self, period=24):
+    #     for label in parking_data_labels:
+    #         self.df[label + '_lagged_' + str(period)] = self.labels_df[label].shift(periods=period)

data/preprocessing/single_prediction_features.py

@@ -50,18 +50,18 @@ def get_weather_forecast(self, timestamp):
         daily_dataframe = pd.DataFrame(data=daily_data)
         return daily_dataframe
 
-    def get_parking_data_df(self):
-        df_parking_data = pd.read_csv("temp-for-lagged.csv", sep=";")
-        df_parking_data["datetime"] = pd.to_datetime(df_parking_data["datetime"], format='%d.%m.%Y %H:%M')
-
-        df_parking_data.set_index("datetime", inplace=True)
-
-        # df = pd.merge(df, df_parking_data, on="datetime", how="outer")
-
-        print("df_parking_data")
-        print(df_parking_data.head())
-
-        return df_parking_data
+    # def get_parking_data_df(self):
+    #     df_parking_data = pd.read_csv("temp-for-lagged.csv", sep=";")
+    #     df_parking_data["datetime"] = pd.to_datetime(df_parking_data["datetime"], format='%d.%m.%Y %H:%M')
+    #
+    #     df_parking_data.set_index("datetime", inplace=True)
+    #
+    #     # df = pd.merge(df, df_parking_data, on="datetime", how="outer")
+    #
+    #     print("df_parking_data")
+    #     print(df_parking_data.head())
+    #
+    #     return df_parking_data
 
     def build_dataframe(self, input_date):
         timestamp = datetime.strptime(input_date, '%Y-%m-%d %H:%M')
@@ -72,7 +72,7 @@ def build_dataframe(self, input_date):
         # Merge Weather with other Features
         df = pd.merge(df_weather, self.calendar_features, on="date", how="left")
         df["datetime"] = timestamp
-        #df["datetime"] = pd.to_datetime(timestamp, format='%d.%m.%Y %H:%M')
+        # df["datetime"] = pd.to_datetime(timestamp, format='%d.%m.%Y %H:%M')
 
         # parking_df = self.get_parking_data_df()
 
@@ -84,8 +84,8 @@ def build_dataframe(self, input_date):
     date_today = date.today()
     date_tomorrow = date_today + timedelta(days=1)
     single_prediction_features = SinglePredictionFeatures("raw_features_2024.csv")
-    print(date_tomorrow.strftime("%Y-%m-%d %H:%M"))
-    print(date_today.strftime("%Y-%m-%d %H:%M"))
+    # print(date_tomorrow.strftime("%Y-%m-%d %H:%M"))
+    # print(date_today.strftime("%Y-%m-%d %H:%M"))
     df_demo, features_length = single_prediction_features.build_dataframe(date_tomorrow.strftime("%Y-%m-%d %H:%M"))
     print(df_demo.head())
     print(df_demo.columns)

model/W&B_PPSG_LSTM.ipynb

@@ -88,6 +88,7 @@
    "outputs": [],
    "source": [
     "# See also https://towardsdatascience.com/choosing-the-right-hyperparameters-for-a-simple-lstm-using-keras-f8e9ed76f046\n",
+    "# Runs are here: https://wandb.ai/parcaster/pp-sg-lstm\n",
     "\n",
     "sweep_config = {\n",
     "    'method': 'bayes',\n",
@@ -97,7 +98,7 @@
     "    },\n",
     "    'parameters': {\n",
     "        'model': {\n",
-    "            'values': ['lstm', 'rnn']\n",
+    "            'value': 'lstm'\n",
     "        },\n",
     "        'scaler': {\n",
     "            'values': ['standard', 'minmax', 'robust', 'maxabs']\n",
@@ -515,7 +516,7 @@
    },
    "outputs": [],
    "source": [
-    "wandb.agent(sweep_id, train, count=1)"
+    "wandb.agent(sweep_id, train, count=20)"
    ]
   },
   {

model/scaler.py

@@ -1,10 +1,8 @@
 import joblib
-from sklearn.preprocessing import StandardScaler
 
 
 class Scaler:
     def __init__(self, scaler):
-        # self.scaler = StandardScaler()
         self.scaler = scaler
 
     def scale(self, X_train, X_val, X_test, y_train, y_val, y_test):