# -*- coding: utf-8 -*-
"""
@author: Rafsan Mazumder

@project: Decision Tree Classifier for Monthly Model

"""

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from IPython.display import display
import sklearn

from sklearn.tree import DecisionTreeClassifier # Import Decision Tree Classifier
from sklearn.model_selection import train_test_split # Import train_test_split function
from sklearn import metrics #Import scikit-learn metrics module for accuracy calculation

from sklearn.model_selection import validation_curve
from sklearn.datasets import load_iris
from sklearn.linear_model import Ridge

datasets = pd.read_csv("C:/Users/BOT/Desktop/Machine Learning/Rainfall Prediction/testMonthly.csv")

label = datasets.loc[:, "Rainfall"]
features = datasets.loc[:, :"Month"]

numpy_label = label.as_matrix()
numpy_features = features.as_matrix()

sizeRow = 16755

blockSize = 700

for index in range(0, sizeRow):
  numpy_label[index] = numpy_label[index] / blockSize

X = numpy_features
y = numpy_label

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)

# Create Decision Tree classifer object
clf = DecisionTreeClassifier()

# Train Decision Tree Classifer
clf = clf.fit(X_train,y_train)

#Predict the response for test dataset
y_pred = clf.predict(X_test)

print("Accuracy:",metrics.accuracy_score(y_test, y_pred))