Tree's problem.txt

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
from sklearn.metrics import accuracy_score
import warnings

warnings.filterwarnings("ignore")

data1 = pd.read_csv('datasets/weather.numeric.csv')
data2 = pd.read_csv('datasets/weather.nominal.csv')


X= data1.drop(columns=['play'], axis=1)

y= data1['play']

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

d1tree= DecisionTreeClassifier()
d1tree.fit(X_train,y_train)
predictions= d1tree.predict(X_test)

tree.plot_tree(d1tree)
plt.show()

from sklearn.metrics import classification_report, confusion_matrix
print("Accuracy:",accuracy_score(y_test,predictions))

print(confusion_matrix(y_test,predictions))
print('\n')
print(classification_report(y_test,predictions))

from sklearn import preprocessing
string_to_int= preprocessing.LabelEncoder()    #encode your data
data2=data2.apply(string_to_int.fit_transform) #fit and transform it

#To divide our data into attribute set and Label:
feature_cols = ['outlook','temperature','humidity','windy']
X = data2[feature_cols]                               #contains the attribute 
y = data2.play                                #contains the label

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30) 

d2tree =DecisionTreeClassifier(criterion="entropy", random_state=100)     # create a classifier object
d2tree.fit(X_train, y_train) 

y_pred= d2tree.predict(X_test)  


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

print(confusion_matrix(y_test, y_pred))  
print(classification_report(y_test, y_pred)) 

tree.plot_tree(d2tree)
plt.show()