Updated app.py

app.py

@@ -0,0 +1,123 @@
+import streamlit as st
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder, StandardScaler
+from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics import confusion_matrix, classification_report
+import matplotlib.pyplot as plt
+import seaborn as sns
+import re
+
+st.title("Expense Category Prediction")
+
+# Load data from CSV
+df = pd.read_csv("financial_data.csv", sep='\s\s+', engine='python')
+
+# Data Preprocessing
+def preprocess_data(df):
+
+    # Clean the date column
+    df['Date'] = df['Date'].str.extract(r'(\d{4}-\d{2}-\d{2})')
+    
+    # Forward fill missing dates
+    df['Date'] = df['Date'].ffill()
+    
+    # Remove rows with missing dates
+    df.dropna(subset=['Date'], inplace=True)
+    
+    # Convert 'Date' to datetime objects
+    df['Date'] = pd.to_datetime(df['Date'])
+
+    # Fill missing values in 'Expense_Category' and 'Description' with 'Unknown'
+    df['Expense_Category'] = df['Expense_Category'].fillna('Unknown')
+    df['Description'] = df['Description'].fillna('Unknown')
+
+    # Convert 'Amount' to numeric, fill missing with 0
+    df['Amount'] = pd.to_numeric(df['Amount'], errors='coerce').fillna(0)
+    
+    # Date Feature Engineering
+    df['Month'] = df['Date'].dt.month
+    df['DayOfWeek'] = df['Date'].dt.dayofweek
+
+    # Description Text Processing
+    def clean_text(text):
+        text = text.lower()
+        text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
+        return text
+
+    df['Description_Cleaned'] = df['Description'].apply(clean_text)
+
+    # TF-IDF Vectorization
+    tfidf_vectorizer = TfidfVectorizer(max_features=100)  # Limiting features for simplicity
+    tfidf_features = tfidf_vectorizer.fit_transform(df['Description_Cleaned']).toarray()
+    tfidf_df = pd.DataFrame(tfidf_features, index=df.index)
+
+    # Combine Features
+    features_df = pd.concat([df[['Amount', 'Month', 'DayOfWeek']], tfidf_df], axis=1)
+
+    # Encode the target variable
+    label_encoder = LabelEncoder()
+    df['Expense_Category_Encoded'] = label_encoder.fit_transform(df['Expense_Category'])
+
+    # Select features and target
+    X = features_df
+    y = df['Expense_Category_Encoded']
+
+    # Scale the features
+    scaler = StandardScaler()
+    X = scaler.fit_transform(X)
+
+    return X, y, label_encoder, df  # Return the original dataframe
+
+X, y, label_encoder, df = preprocess_data(df.copy())
+
+# Split data
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.2, random_state=42)
+
+# --- Models ---
+models = {
+    "Random Forest": RandomForestClassifier(random_state=42),
+    "Gradient Boosting": GradientBoostingClassifier(random_state=42)
+}
+
+# --- Streamlit Tabs ---
+tabs = st.tabs(list(models.keys()))
+
+for tab, model_name in zip(tabs, models.keys()):
+    with tab:
+        st.header(model_name)
+        model = models[model_name]
+        model.fit(X_train, y_train)
+        y_pred = model.predict(X_test)
+
+        # --- Confusion Matrix ---
+        st.subheader("Confusion Matrix")
+        cm = confusion_matrix(y_test, y_pred)
+        plt.figure(figsize=(8, 6))
+        sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")
+        plt.xlabel("Predicted")
+        plt.ylabel("Actual")
+        st.pyplot(plt.gcf())
+
+        # --- Classification Report ---
+        st.subheader("Classification Report")
+        cr = classification_report(y_test, y_pred,
+                                   target_names=label_encoder.inverse_transform(
+                                       df['Expense_Category_Encoded'].unique()),
+                                   zero_division=0)  # Get original category names
+        st.text(cr)
+
+        # --- Remarks ---
+        st.subheader("Remarks")
+        st.write("Model Performance Analysis:")
+        st.write(
+            f"The {model_name} model's performance in predicting Expense Categories is shown above.")
+        st.write("Key Metrics:")
+        st.write(
+            "-   The model uses a combination of expense amount, time-based features, and text descriptions to predict the expense category."
+        )
+        st.write(
+            "-   The classification report provides insights into the model's precision, recall, and F1-score for each expense category."
+        )