import pandas as pd
#import numpy as np
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn import preprocessing


raw_data=pd.read_csv('student_mark_result_dec_hist.csv',index_col=False)
blankIndex=[''] * len(raw_data)
raw_data.index=blankIndex

le = preprocessing.LabelEncoder()

for column_name in raw_data.columns:
	if raw_data[column_name].dtype == object:
		raw_data[column_name] = le.fit_transform(raw_data[column_name])
		le_name_mapping = dict(zip(le.classes_, le.transform(le.classes_)))
		print(le_name_mapping)
		
	else:
		pass
print('---->', raw_data[:])

X=raw_data[['name','day','subject']]
y=raw_data['percentage']

model=DecisionTreeRegressor()
model.fit(X,y)

predictions=model.predict([  [0,24,0], [0,-1,0]  ])
print(predictions)

#here, i am not sure if [0.24.0],[0,-1,0] points to date 12/25/2019 and 11/30/2019, Any ideas?