Download Decision Tree Machine Learning and more Study notes Machine Learning in PDF only on Docsity!
In [2]: In [3]: In [4]: In [5]: In [6]: RID age income student credit_rating buys_computer 0 1 youth high no fair no 1 2 youth high no excellent no 2 3 middle_aged high no fair yes 3 4 senior medium no fair yes 4 5 senior low yes fair yes 5 6 senior low yes excellent no 6 7 middle_aged low yes excellent yes 7 8 youth medium no fair no 8 9 youth low yes fair yes 9 10 senior medium yes fair yes 10 11 youth medium yes excellent yes 11 12 middle_aged medium no excellent yes 12 13 middle_aged high yes fair yes 13 14 senior medium no excellent no import pandas as pd import matplotlib.pyplot as plt data = pd.read_excel('C:/Users/kriti/OneDrive/Desktop/machine Learning/experiments/dt. print(data) #Encode the text or non numerical data into numerical value from sklearn.preprocessing import LabelEncoder # created instances for class LableEncoder le_age = LabelEncoder() le_income = LabelEncoder() le_student = LabelEncoder() le_credit_rating = LabelEncoder() le_buys_computer = LabelEncoder()
In [8]: In [9]: Out[8]: RID age income student credit_rating buys_computer age_n income_n stude 0 1 youth high no fair no 2 0 1 2 youth high no excellent no 2 0 2 3 middle_aged high no fair yes 0 0 3 4 senior medium no fair yes 1 2 4 5 senior low yes fair yes 1 1 Out[9]: RID age_n income_n student_n credit_rating_n buys_computer_n 0 1 2 0 0 1 0 1 2 2 0 0 0 0 2 3 0 0 0 1 1 3 4 1 2 0 1 1 4 5 1 1 1 1 1 5 6 1 1 1 0 0 6 7 0 1 1 0 1 7 8 2 2 0 1 0 8 9 2 1 1 1 1 9 10 1 2 1 1 1 10 11 2 2 1 0 1 11 12 0 2 0 0 1 12 13 0 0 1 1 1 13 14 1 2 0 0 0 # fit_tranform data['age_n'] = le_age.fit_transform(data['age']) data['income_n'] = le_income.fit_transform(data['income']) data['student_n'] = le_student.fit_transform(data['student']) data['credit_rating_n'] = le_credit_rating.fit_transform(data['credit_rating']) data['buys_computer_n'] = le_buys_computer.fit_transform(data['buys_computer']) data.head() data_new = data.drop(['age','income','student','credit_rating','buys_computer'],axis = 1 data_new
In [14]: In [15]: In [16]: Out[15]: age_n income_n student_n credit_rating_n 5 1 1 1 0 8 2 1 1 1 2 0 0 0 1 1 2 0 0 0 13 1 2 0 0 4 1 1 1 1 7 2 2 0 1 10 2 2 1 0 3 1 2 0 1 6 0 1 1 0 Out[16]: 5 0 8 1 2 1 1 0 13 0 4 1 7 0 10 1 3 1 6 1 Name: buys_computer_n, dtype: int # for splitting from sklearn.model_selection import train_test_split x_train, x_test, y_train, y_test = train_test_split(x,y,test_size = 0.25,random_state = x_train y_train
In [18]: In [19]: Out[17]: age_n income_n student_n credit_rating_n 9 1 2 1 1 11 0 2 0 0 0 2 0 0 1 12 0 0 1 1 Out[18]: 9 1 11 1 0 0 12 1 Name: buys_computer_n, dtype: int Out[19]: age_n income_n student_n credit_rating_n buys_computer_n 5 1 1 1 0 0 8 2 1 1 1 1 2 0 0 0 1 1 1 2 0 0 0 0 13 1 2 0 0 0 4 1 1 1 1 1 7 2 2 0 1 0 10 2 2 1 0 1 3 1 2 0 1 1 6 0 1 1 0 1 x_test y_test # concatenating the training dataset pd.concat([x_train, y_train], axis = 1 )
cm = confusion_matrix(y_test, y_pred) plt.figure(figsize = ( 5 , 5 )) sns.heatmap(data = cm, annot = True , cmap = 'Blues') plt.ylabel('Actual values') plt.xlabel('predicted values') plt.show()
In [ ]: #graphical visualization of tree from sklearn.tree import plot_tree # help you to produce the figure of tree plt.figure(figsize = ( 12 , 12 )) dec_tree = plot_tree(decision_tree = dt,feature_names = feature_cols,class_names = ["0","1"] filled =True ,rounded =True )
