K-MEANS CLUSTERING
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans
X, y_true = make_blobs(n_samples=300, centers=4, cluster_std=0.6, random_state=0)
kmeans = KMeans(n_clusters=4)
kmeans.fit(X)
labels = kmeans.labels_
centers = kmeans.cluster_centers_
plt.scatter(X[:, 0], X[:, 1], c=labels, cmap=’viridis’)
plt.scatter(centers[:, 0], centers[:, 1], marker=’X’, color=’red’, s=200)
plt.title(“K-means Clustering”)
plt.xlabel(“Feature 1”)
plt.ylabel(“Feature 2”)
plt.show()
Decision trees
import warnings
warnings.filterwarnings(“ignore”)
# Importing the required packages
import numpy as np
import pandas as pd
from sklearn.metrics import confusion_matrix
from sklearn.cross_validation import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
# Function importing Dataset
def importdata():
balance_data = pd.read_csv(‘https://archive.ics.uci.edu/ml/machine-learning-databases/balance-sca
le/balance-scale.data’,
sep= ‘,’, header = None)
# Printing the dataswet shape
print (“Dataset Lenght: “, len(balance_data))
print (“Dataset Shape: “, balance_data.shape)
print (“Dataset: “,balance_data.head())
return balance_data
def splitdataset(balance_data):
X = balance_data.values[:, 1:5]
Y = balance_data.values[:, 0]
X_train, X_test, y_train, y_test = train_test_split(
X, Y, test_size = 0.3, random_state = 100)
return X, Y, X_train, X_test, y_train, y_test
def train_using_gini(X_train, X_test, y_train):
clf_gini = DecisionTreeClassifier(criterion = “gini”,
random_state = 100,max_depth=3, min_samples_leaf=5)
clf_gini.fit(X_train, y_train)
return clf_gini
def tarin_using_entropy(X_train, X_test, y_train):
clf_entropy = DecisionTreeClassifier(
criterion = “entropy”, random_state = 100,
max_depth = 3, min_samples_leaf = 5)
clf_entropy.fit(X_train, y_train)
return clf_entropy
def prediction(X_test, clf_object):
y_pred = clf_object.predict(X_test)
print(“Predicted values:”)
print(y_pred)
return y_pred
return y_pred
def cal_accuracy(y_test, y_pred):
print(“Confusion Matrix: “,
confusion_matrix(y_test, y_pred))
print (“Accuracy : “,
accuracy_score(y_test,y_pred)*100)
print(“Report : “,
classification_report(y_test, y_pred))
def main():
data = importdata()
X, Y, X_train, X_test, y_train, y_test = splitdataset(data)
clf_gini = train_using_gini(X_train, X_test, y_train)
clf_entropy = tarin_using_entropy(X_train, X_test, y_train)
print(“Results Using Gini Index:”)
y_pred_gini = prediction(X_test, clf_gini)
cal_accuracy(y_test, y_pred_gini)
print(“Results Using Entropy:”)
y_pred_entropy = prediction(X_test, clf_entropy)
cal_accuracy(y_test, y_pred_entropy)
if _name==”main_”:
main()
