hide api keys

src/.env

@@ -0,0 +1,2 @@
+SENTIMENT_KEY=22f6dfa7bb114867a3bcb7c56b6c6410
+GPT_KEY=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

src/fetch_sentiment_data.py

@@ -2,11 +2,14 @@
 from textblob import TextBlob
 import pandas as pd
 from datetime import datetime, timedelta
+from dotenv import load_dotenv
 import os
 
+# Load environment variables from .env
+load_dotenv()
 
 # Function to fetch news headlines for a specific date
-def fetch_news(api_key, date):
+def fetch_news(date):
     all_headlines = []
     url = "https://newsapi.org/v2/everything"
     params = {
@@ -15,7 +18,7 @@ def fetch_news(api_key, date):
         "to": date,
         "sortBy": "publishedAt",
         "language": "en",
-        "apiKey": api_key,
+        "apiKey": os.getenv("SENTIMENT_KEY"),  # Use environment variable
     }
     response = requests.get(url, params=params)
     if response.status_code == 200:
@@ -26,15 +29,13 @@ def fetch_news(api_key, date):
         print(f"Failed to fetch news for {date}")
     return all_headlines
 
-
 # Function to calculate average sentiment score for headlines
 def average_sentiment(headlines):
     sentiment_scores = [TextBlob(headline).sentiment.polarity for headline in headlines]
     return sum(sentiment_scores) / len(sentiment_scores) if sentiment_scores else 0
 
-
 # Main function to fetch, process news headlines, and save to CSV
-def main(api_key):
+def main():
     end_date = datetime.now()
     start_date = end_date - timedelta(days=30)
 
@@ -45,7 +46,7 @@ def main(api_key):
 
     for date in dates:
         date_str = date.strftime("%Y-%m-%d")
-        headlines = fetch_news(api_key, date_str)
+        headlines = fetch_news(date_str)
         if headlines:  # Proceed if there are headlines for the day
             avg_sentiment = average_sentiment(headlines)
             average_sentiments.append(
@@ -75,5 +76,4 @@ def main(api_key):
 
 
 if __name__ == "__main__":
-    api_key = "22f6dfa7bb114867a3bcb7c56b6c6410"
-    main(api_key)
+    main()

src/gpt.py

@@ -1,29 +1,29 @@
 import os
 from openai import OpenAI
 import pandas as pd
+from dotenv import load_dotenv
 
+# Load environment variables from .env
+load_dotenv()
 
 # Function to load data from the combined CSV file
 def load_data(combined_data_path, linear_regression_data):
     df_combined = pd.read_csv(combined_data_path)
     df_linear = pd.read_csv(linear_regression_data)
     return df_combined, df_linear
 
-
 # Function to create summaries or extract relevant data
 def summarize_data(df_combined, df_linear):
     combined_summary = df_combined.describe().to_string()
     linear_regression_summary = df_linear.describe().to_string()
     return combined_summary, linear_regression_summary
 
-
 # Function to set up OpenAI API key
-def setup_openai_api(api_key):
-    os.environ["OPENAI_API_KEY"] = api_key
-
+def setup_openai_api():
+    os.environ["OPENAI_API_KEY"] = os.getenv("GPT_KEY")  # Use environment variable
 
 # Function to make predictions using OpenAI
-def make_prediction(combined_summary, linear_regression_summary):
+def make_prediction():
     client = OpenAI()
     completion = client.chat.completions.create(
         model="gpt-3.5-turbo",
@@ -40,7 +40,6 @@ def make_prediction(combined_summary, linear_regression_summary):
     )
     return completion.choices[0].message
 
-
 # Main function to orchestrate the modular components
 def main():
     # Get the current directory of the script
@@ -60,10 +59,10 @@ def main():
     combined_summary, linear_regression_summary = summarize_data(df_combined, df_linear)
 
     # Set up OpenAI API key
-    setup_openai_api("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")
+    setup_openai_api()
 
     # Make a prediction
-    prediction = make_prediction(combined_summary, linear_regression_summary)
+    prediction = make_prediction()
 
     # Save prediction results to CSV
     prediction_df = pd.DataFrame({"Prediction": [prediction]})
@@ -75,4 +74,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

src/predict_closing_price.py

@@ -5,43 +5,28 @@
 from sklearn.metrics import mean_squared_error
 from datetime import datetime
 
-
 # Function to load data from the combined CSV file
 def load_data(combined_data_path):
     df_combined = pd.read_csv(combined_data_path)
     return df_combined
 
-
-# Function to split data into training and testing sets
-def split_data(df_combined):
-    features = df_combined[["Average Sentiment", "Volume"]]
-    target = df_combined["Close"]
-    X_train, X_test, y_train, y_test = train_test_split(
-        features, target, test_size=0.2, random_state=42
-    )
-    return X_train, X_test, y_train, y_test
-
-
 # Function to train a linear regression model
 def train_model(X_train, y_train):
     model = LinearRegression()
     model.fit(X_train, y_train)
     return model
 
-
 # Function to evaluate the model's performance
 def evaluate_model(model, X_test, y_test):
     predictions = model.predict(X_test)
     mse = mean_squared_error(y_test, predictions)
     return mse
 
-
 # Function to predict the next day's closing price
 def predict_next_day_closing_price(model, next_day_features):
     predicted_closing_price = model.predict([next_day_features])
     return predicted_closing_price
 
-
 # Main function to orchestrate the process
 def main():
     # Get the current directory of the script
@@ -54,8 +39,12 @@ def main():
     # Load the data
     df_combined = load_data(combined_data_path)
 
-    # Split the data into training and testing sets
-    X_train, X_test, y_train, y_test = split_data(df_combined)
+    # Features and target
+    X = df_combined[['Average Sentiment', 'Volume']]
+    y = df_combined['Close']
+
+    # Train/test split
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
     # Train the linear regression model
     model = train_model(X_train, y_train)
@@ -65,10 +54,7 @@ def main():
     print(f"Mean Squared Error: {mse}")
 
     # Example: Features for the next day
-    next_day_features = [
-        0.2,
-        10000,
-    ]  # Example values for 'Average Sentiment' and 'Volume'
+    next_day_features = [0.2, 10000]  # Example values for 'Average Sentiment' and 'Volume'
 
     # Predict the next day's closing price
     next_day_closing_price = predict_next_day_closing_price(model, next_day_features)