error handling

app.py

@@ -1,68 +1,126 @@
 import numpy as np
 import pandas as pd
-import streamlit as st
 import plotly.express as px
-from sklearn.model_selection import train_test_split
-from sklearn import preprocessing
+import streamlit as st
 import yfinance as yf
+from sklearn import preprocessing
 from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
 
 # Streamlit app
-st.title('CUSTOM Stock Price Prediction 💰')
-st.write('This model predicts upon trends. It will not perform well in volatile history. setting the time frame "max" is recommended. Your predicted days value can not exceed the time frame days. Have fun!')
+st.title("CUSTOM Stock Price Prediction 💰")
+st.write(
+    'This model predicts based on trends. It may not perform well with volatile history. Setting the time frame to "max" is recommended. Your predicted days value cannot exceed the time frame days. Have fun!'
+)
+
 # Input widgets
-stock = st.text_input('Stock tag', value='NVDA')
-daysago = st.text_input('Time frame in days (write "max" for max time)', value='365')
-forecast_out = st.number_input('Predicted days', value=180,min_value=1)
-forecast_col = 'Close'
-
-def prepare_data(df,forecast_col,forecast_out):
-    label = df[forecast_col].shift(-forecast_out) #creating new column called label with the last 5 rows are nan
-    X = np.array(df[[forecast_col]]) #creating the feature array
-    X = preprocessing.scale(X) #processing the feature array
-    X_lately = X[-forecast_out:] #creating the column i want to use later in the predicting method
-    X = X[:-forecast_out] # X that will contain the training and testing
-    label.dropna(inplace=True) #dropping na values
-    y = np.array(label)  # assigning Y
-    X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=0.2, random_state=42) #cross validation
-
-    response = [X_train,X_test , Y_train, Y_test , X_lately]
-    return response
+stock = st.text_input("Stock ticker symbol", value="NVDA")
+daysago = st.text_input(
+    'Time frame in days (write "max" for maximum time)', value="365"
+)
+forecast_out = st.number_input("Predicted days", value=180, min_value=1)
+forecast_col = "Close"
+
+
+def prepare_data(df, forecast_col, forecast_out):
+    # Check if the dataframe is empty or too small for forecast
+    if df.empty or len(df) <= forecast_out:
+        st.error("Insufficient data available for the given forecast period.")
+        return None, None, None, None, None
+
+    label = df[forecast_col].shift(
+        -forecast_out
+    )  # Shift the column to create a future prediction label
+    X = np.array(df[[forecast_col]])  # Create feature array
+
+    # Check if X has enough samples
+    if X.shape[0] == 0:
+        st.error("No data available for scaling.")
+        return None, None, None, None, None
+
+    X = preprocessing.scale(X)  # Scale the feature array
+    X_lately = X[-forecast_out:]  # The data that will be predicted on
+    X = X[:-forecast_out]  # Training data
+    label.dropna(inplace=True)  # Drop NaN values from the label
+
+    y = np.array(label)  # Target array
+
+    # Check if we have enough data for train-test split
+    if len(y) == 0 or len(X) == 0:
+        st.error(
+            "Not enough data for training. Adjust the forecast period or date range."
+        )
+        return None, None, None, None, None
+
+    X_train, X_test, Y_train, Y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42
+    )  # Train/test split
+
+    return X_train, X_test, Y_train, Y_test, X_lately
+
 
 # Button to trigger model generation and prediction
-if st.button('Generate'):
+if st.button("Generate"):
     # Fetch stock data
-    if daysago != 'max':
-        daysago = str(daysago) + 'd'
+    if daysago != "max":
+        daysago = str(daysago) + "d"
 
     ticker = yf.Ticker(stock)
     data = ticker.history(period=daysago)
 
-    X_train, X_test, Y_train, Y_test , X_lately =prepare_data(data,forecast_col,forecast_out); #calling the method were the cross validation and data preperation is in
+    if data.empty:
+        st.error(
+            "Failed to retrieve data for the ticker symbol. Please check the stock symbol and try again."
+        )
+    else:
+        X_train, X_test, Y_train, Y_test, X_lately = prepare_data(
+            data, forecast_col, forecast_out
+        )  # Call data preparation method
+
+        if X_train is not None:
+            # Model generation
+            learner = LinearRegression()
+            learner.fit(X_train, Y_train)
+            score = learner.score(X_test, Y_test)
+            forecast = learner.predict(X_lately)
 
-    # Model Generation
-    learner = LinearRegression()
-    learner.fit(X_train, Y_train)
-    score = learner.score(X_test, Y_test)
-    forecast = learner.predict(X_lately)
-    #st.write('Used Model:', selected_algorithm)
-    st.write('Accuracy Score:', score)
+            st.write("Accuracy Score:", score)
 
-    #GRAPH
-    # Create a DataFrame with future dates and predicted values
-    future_dates = pd.date_range(start=data.index[-1] + pd.Timedelta(days=1), periods=forecast_out, freq='D')
-    predicted_data = pd.DataFrame({'Date': future_dates, 'Predicted Close': forecast})
+            # Create a DataFrame with future dates and predicted values
+            future_dates = pd.date_range(
+                start=data.index[-1] + pd.Timedelta(days=1),
+                periods=forecast_out,
+                freq="D",
+            )
+            predicted_data = pd.DataFrame(
+                {"Date": future_dates, "Predicted Close": forecast}
+            )
 
-    # Concatenate original data and predicted data
-    combined_data = pd.concat([data.rename(columns={'Close': 'Actual Close'}), predicted_data.set_index('Date')], axis=1)
+            # Concatenate original data and predicted data
+            combined_data = pd.concat(
+                [
+                    data.rename(columns={"Close": "Actual Close"}),
+                    predicted_data.set_index("Date"),
+                ],
+                axis=1,
+            )
 
-    # Plot original and predicted stock prices
-    fig = px.line(combined_data, x=combined_data.index, y=['Actual Close', 'Predicted Close'], title=f'Predicted {stock} Stock Prices')
-    fig.update_layout(xaxis_title='Date',yaxis_title='Price',legend_title_text='')
+            # Plot original and predicted stock prices
+            fig = px.line(
+                combined_data,
+                x=combined_data.index,
+                y=["Actual Close", "Predicted Close"],
+                title=f"Predicted {stock} Stock Prices",
+            )
+            fig.update_layout(
+                xaxis_title="Date", yaxis_title="Price", legend_title_text=""
+            )
 
-    # Set line colors
-    fig.data[1].line.color = 'orange'
+            # Set line colors
+            fig.data[1].line.color = "orange"
 
-    st.plotly_chart(fig)
+            st.plotly_chart(fig)
 
-    st.write('Findings: I tried using pycaret.regression to model, interestingly the r2 score of KNeighborsRegressor() was always the highest, with 96%, but it clearly gave a wrong output. Methods other than Ridge, Lasso and Linear Regression seem to always fail so I decied to stick with Linear Regression despite its 88% acc. score. It is not always correct, if the stock price has lots of ups and downs, it wont be able to give a good estimate as the accuracy score often goes below 50%. The discrepancy can be understood by the disconnection between the lines actual close and predicted close. It needs deep learning to go ruther.')
+            st.write(
+                "Findings: Linear Regression often performs poorly on volatile stock prices, so this model may not be highly accurate for certain stocks. Consider using deep learning methods for improved accuracy on volatile stocks."
+            )