Update observatory_app.py

observatory_app.py

@@ -9,9 +9,10 @@ from textblob import TextBlob
 from sklearn.linear_model import Ridge
 from sklearn.model_selection import train_test_split
 
-@st.cache_data 
+data_url = "https://raw.githubusercontent.com/KeeganBarbee/KeeganBarbee.github.io/refs/heads/main/OnlineNewsPopularity.csv"
+@st.cache_data(ttl = 3600) 
 def load_data():
-    df = pd.read_csv("OnlineNewsPopularity.csv")
+    df = pd.read_csv(data_url)
     df.columns = df.columns.str.strip()
     
     channel_cols = ['data_channel_is_lifestyle', 'data_channel_is_entertainment',
@@ -33,9 +34,8 @@ def load_data():
     df['day_of_week'] = df.apply(get_day, axis=1)
     return df[df['shares'] < 20000]
 
-df_display = load_data()
-df = pd.read_csv("OnlineNewsPopularity.csv")
-df.columns = df.columns.str.strip()
+df = pd.read_csv(data_url)
+df_display = df.copy()
 
 df['log_shares'] = np.log1p(df['shares'])
 
@@ -43,18 +43,11 @@ feature_cols = [
     'n_tokens_content', 'num_imgs', 'global_sentiment_polarity', 
     'global_subjectivity', 'title_sentiment_polarity', 'weekday_is_monday', 'weekday_is_tuesday', 'weekday_is_wednesday',
     'weekday_is_thursday', 'weekday_is_friday', 'weekday_is_saturday', 'weekday_is_sunday', 'n_tokens_title', 
-    'num_videos', 'num_imgs', 'num_hrefs'
+    'num_videos', 'num_hrefs'
 ]
 x = df[feature_cols]
 y = df['log_shares']
 
-X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
-model = Ridge(alpha=1.0)
-model.fit(X_train, y_train)
-
-joblib.dump(model, 'popularity_model.pkl')
-joblib.dump(x.columns.tolist(), 'model_features.pkl')
-
 model = joblib.load('popularity_model.pkl')
 feature_columns = joblib.load('model_features.pkl')