final models

IT20074340/TaskAllocation/Sachintha/model/train.py

+from flask import Flask, jsonify, request
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.svm import SVC
+from sklearn.model_selection import train_test_split
+from sklearn.model_selection import GridSearchCV
+import pickle
+
+app = Flask(__name__)
+
+
+def save_pickle(obj, filename):
+    with open(filename, 'wb') as file:
+        pickle.dump(obj, file)
+
+
+def train_model(data_path):
+    # Load and preprocess the data
+    df = pd.read_csv(data_path)
+    X_train, _, y_train, _ = train_test_split(df['TaskDescription'], df['Level'], test_size=0.2, random_state=42)
+    vectorizer = TfidfVectorizer()
+    X_train_vec = vectorizer.fit_transform(X_train)
+
+    # Initialize GridSearchCV
+    param_grid = {'C': [0.1, 1, 10, 100, 1000],
+                  'gamma': [1, 0.1, 0.01, 0.001, 0.0001],
+                  'kernel': ['linear', 'rbf', 'sigmoid']}
+    grid = GridSearchCV(SVC(), param_grid, refit=True, verbose=3)
+    grid.fit(X_train_vec, y_train)
+
+    # Save the trained classifier and vectorizer as .pickle files
+    save_pickle(grid, 'classifier.pickle')
+    save_pickle(vectorizer, 'vectorizer.pickle')
+
+    return 'Model trained and saved successfully'
+
+
+@app.route('/train', methods=['GET'])
+def trigger_training():
+    try:
+        result = train_model("TaskDescCopy3.csv")
+        return jsonify({'message': result})
+    except Exception as e:
+        return jsonify({'error': str(e)})
+
+
+if __name__ == '__main__':
+    app.run(host='127.0.0.1', port=5001, debug=False)