si_lab03

import pandas as pd
import numpy as np
from sklearn.neighbors import KNeighborsClassifier as kNN
from sklearn.svm import SVC as SVM
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
col_names = ['Gender', 'Married', 'Education', 'Self_Employed', 'Loan_Status']
col_values = ['Male', 'Yes', 'Graduate', 'Yes', 'Y']
pd.options.mode.chained_assignment = None
data = pd.read_excel('loan_data.xlsx');
for i in range(len(col_names)):
    mask = data[col_names[i]].values == col_values[i]
    data[col_names[i]][mask] = 0
    data[col_names[i]][~mask] = 1
columns = list(data.columns);
# mask = data ['Gender'].values == 'Female'
# data['Gender'][mask] = 1
# data['Gender'][~mask] = 0
cat_feature = pd.Categorical(data.Property_Area)
one_hot = pd.get_dummies(cat_feature)
data = pd.concat([data, one_hot], axis = 1)
data = data.drop(columns = ['Property_Area'])
features = data.columns
vals = data.values.astype(np.float64)
X = vals[:, :-1]
y = vals[:,-1]
models = [kNN(), SVM()]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
for model in models:
    model.fit(X_train,y_train)
    y_pred = model.predict(X_test)
    print(confusion_matrix(y_test, y_pred))
from sklearn.tree import DecisionTreeClassifier as DT
from sklearn.tree import plot_tree
model = DT(max_depth=3)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
cm = confusion_matrix(y_test, y_pred)
print(cm)
from matplotlib import pyplot as plt
plt.figure(figsize=(20,10))
tree_vis = plot_tree(model,feature_names=
 data.columns[:-1],class_names=['N', 'Y'], fontsize = 20)