I am trying to create a web application on Python using Flask that predicts if a student is likely to pass or fail using a Kaggle dataset. I changed the dataset a little and want to predict if the student will Pass or Fail using Logistic Regression by setting all students with Average marks (calculated as (math score+reading score+writing score)/3) below 45 as fail and others as pass. I also dropped the lunch column. I am getting an error when I run the following code---
model.py
import pandas as pd
import pickle
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
data = pd.read_csv('1. StudentsPerformance main.csv')
target_name='Average Score'
x = data.iloc[:, :3].values
y=data[target_name].values
le = LabelEncoder()
x['Parental Education Level']= le.fit_transform(x['Parental Education Level'])
x['Race/Ethnicity']= le.fit_transform(x['Race/Ethnicity'])
x['Test Preparation Course']= le.fit_transform(x['Test Preparation Course'])
onehotencoder = OneHotEncoder()
x = onehotencoder.fit_transform(x).toarray()
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2,random_state = 40)
print('The number of samples into the train data is {}.'.format(x_train.shape[0]))
print('The number of samples into the test data is {}.'.format(x_test.shape[0]))
from sklearn.linear_model import LogisticRegression
reg=LogisticRegression(n_jobs=-1, random_state=15, solver='lbfgs')
reg.fit(x_train,y_train)
pickle.dump(reg, open('model.pkl','wb'))
#model = pickle.load(open('model.pkl','rb'))
app.py
app = Flask(__name__)
model = pickle.load(open('model.pkl', 'rb'))
@app.route('/')
def home():
return render_template('index.html')
@app.route('/predict',methods=['POST'])
def predict():
'''
For rendering results on HTML GUI
'''
int_features = [int(x) for x in request.form.values()]
final_features = [np.array(int_features)]
prediction = model.predict(final_features)
output = round(prediction[0], 2)
#return render_template('index.html', prediction_text='The student is more likely to PASS')
return render_template('index.html', prediction_text='The student is more likely to $ {}'.format(output))
@app.route('/predict_api',methods=['POST'])
def predict_api():
'''
For direct API calls trought request
'''
data = request.get_json(force=True)
prediction = model.predict([np.array(list(data.values()))])
output = prediction[0]
return jsonify(output)
if __name__ == "__main__":
app.run(debug=True)
index.html
<html>
<head>
<link rel="stylesheet" href="a.css">
<title>Prediction Model</title>
</head>
<body>
<center>
<h4>Prediction Model for StudentPerformance.csv</h4>
<form action="{{ url_for('predict')}}"method="post">
<label for="tpc">Test Preparation Course Status-</label><br>
<select id="tpc" name="tpc">
<option value="0">Complete</option>
<option value="1">None</option>
</select><br>
<label for="pel">Parental Education Level-</label><br>
<select id="pel" name="pel">
<option value="0">High School</option>
<option value="1">Some College</option>
<option value="2">Bachelor's Degree</option>
<option value="3">Associate's Degree</option>
<option value="4">Master's Degree</option>
</select><br>
<label for="re">Race/Ethnicity-</label><br>
<select id="re" name="re">
<option value="0">Group A</option>
<option value="1">Group B</option>
<option value="2">Group C</option>
<option value="3">Group D</option>
<option value="4">Group E</option>
</select><br>
<input type="Submit" value="Submit"><br></form>
<p>Output: </p> <br>
{{ prediction_text }}
</center>
</body>
</html>
request.py
import requests
url = 'http://localhost:5000/predict_api'
r = requests.post(url,json={'tpc':"completed", 'pel':"high school", 're':"group A"})
print(r.json())
Traceback---
Traceback (most recent call last):
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 2463, in __call__
return self.wsgi_app(environ, start_response)
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 2449, in wsgi_app
response = self.handle_exception(e)
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 1866, in handle_exception
reraise(exc_type, exc_value, tb)
File "C:\Users\admin\anaconda3\lib\site-packages\flask\_compat.py", line 39, in reraise
raise value
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 2446, in wsgi_app
response = self.full_dispatch_request()
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 1951, in full_dispatch_request
rv = self.handle_user_exception(e)
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 1820, in handle_user_exception
reraise(exc_type, exc_value, tb)
File "C:\Users\admin\anaconda3\lib\site-packages\flask\_compat.py", line 39, in reraise
raise value
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 1949, in full_dispatch_request
rv = self.dispatch_request()
File "C:\Users\admin\anaconda3\lib\site-packages\flask\app.py", line 1935, in dispatch_request
return self.view_functions[rule.endpoint](**req.view_args)
File "C:\Users\admin\shreyaflask\app.py", line 25, in predict
prediction = model.predict(final_features)
File "C:\Users\admin\anaconda3\lib\site-packages\sklearn\linear_model\_base.py", line 293, in predict
scores = self.decision_function(X)
File "C:\Users\admin\anaconda3\lib\site-packages\sklearn\linear_model\_base.py", line 273, in decision_function
% (X.shape[1], n_features))
ValueError: X has 3 features per sample; expecting 12
