Upload New File

api.py

+from flask import Flask, render_template, Response, request
+from flask_cors import CORS
+import requests as r
+import pickle
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import LabelEncoder
+
+app = Flask(__name__)
+CORS(app)
+
+lr_model = pickle.load(open('trained_models/finalized_model_lr.sav', 'rb'))
+
+final_result_list = [0, 0, 0, 0, 0]
+
+
+@app.route('/')
+def home():
+    return render_template('index.html')
+
+
+@app.route('/classification', methods=['POST'])
+def classification():
+    global emotion_data
+
+    question_no = request.form['question_no']
+    answer = request.form['answer']
+    emotion = request.form['emotion']
+    add_status = request.form['add_status']
+
+    features = data_preprocessing([question_no, answer, emotion])
+    print(features)
+    prediction = lr_model.predict(features)
+
+    if prediction[0] == 1:
+        final_result_list[0] += 1
+    elif prediction[0] == 2:
+        final_result_list[1] += 1
+    elif prediction[0] == 3:
+        final_result_list[2] += 1
+    elif prediction[0] == 4:
+        final_result_list[3] += 1
+    else:
+        final_result_list[4] += 1
+
+    if add_status == 'add':
+        return render_template('index.html')
+    else:
+        return render_template('result_2.html', data=final_result_list)
+
+
+def data_preprocessing(data):
+    df = pd.read_csv('data/reason_data_up.csv')
+
+    # df.loc[len(df.index)] = data
+    df.append(pd.Series(data, index=df.columns[:len(data)]), ignore_index=True)
+
+    df['question no'] = df['question no'].astype('str')
+    df['answer'] = df['answer'].astype('str')
+    df['emotion'] = df['emotion'].astype('str')
+
+    df[['question no', 'answer', 'emotion']] =  df[['question no','answer','emotion']].apply(LabelEncoder().fit_transform)
+
+    X_var = np.asarray(df[['question no', 'answer', 'emotion']])
+
+    return [X_var[-1]]
+
+
+if __name__ == "__main__":
+    app.run(debug=True)