import matplotlib.
pyplot as plt
from sklearn import datasets
from sklearn.cluster import KMeans
import sklearn.metrics as sm
import pandas as pd
import numpy as np
iris = datasets.load_iris()
X = pd.DataFrame(iris.data)
X.columns = ['Sepal_Length','Sepal_Width','Petal_Length','Petal_Width']
y = pd.DataFrame(iris.target)
y.columns = ['Targets']
model = KMeans(n_clusters=3)
model.fit(X)
plt.figure(figsize=(14,7))
colormap = np.array(['red', 'lime', 'black'])
plt.subplot(1, 2, 1)
plt.scatter(X.Petal_Length, X.Petal_Width, c=colormap[y.Targets], s=40)
plt.title('Real Classification')
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')
plt.subplot(1, 2, 2)
plt.scatter(X.Petal_Length, X.Petal_Width, c=colormap[model.labels_], s=40)
plt.title('K Mean Classification')
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')
print('The accuracy score of K-Mean: ',sm.accuracy_score(y, model.labels_))
print('The Confusion matrixof K-Mean: ',sm.confusion_matrix(y, model.labels_))
from sklearn import preprocessing
scaler = preprocessing.StandardScaler()
scaler.fit(X)
xsa = scaler.transform(X)
xs = pd.DataFrame(xsa, columns = X.columns)
#xs.sample(5)
from sklearn.mixture import GaussianMixture
gmm = GaussianMixture(n_components=3)
gmm.fit(xs)
y_gmm = gmm.predict(xs)
plt.subplot(2, 2, 3)
plt.scatter(X.Petal_Length, X.Petal_Width, c=colormap[y_gmm], s=40)
plt.title('GMM Classification')
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')
print('The accuracy score of EM: ',sm.accuracy_score(y, y_gmm))
print('The Confusion matrix of EM: ',sm.confusion_matrix(y, y_gmm))
print('Accuracy Metrics of EM: ',classification_report(y,y_gmm))
Exp-Kmeans Em program
import pandas as pd
import numpy as np
import seaborn as sns
from sklearn.ensemble import RandomForestClassifier
from sklearn import svm
from sklearn.svm import SVC
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import confusion_matrix,accuracy_score,classification_report
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
data=pd.read_csv("IMDBNew.csv")
print(data)
"""
drop Missing values
"""
print(data.dropna(axis=0,inplace=True))
print(data.isnull().sum())
"""
Imputing Missing Values
Revenue_mean=data["Revenue (Millions)"].mean()
print(Revenue_mean)
data["Revenue (Millions)"].fillna(Revenue_mean,inplace=True)
print(data.isnull().sum())
"""
"""
Preprocessing Data
"""
bins=(10,50,100)
group_name=[0,1]
data['Metascore']=pd.cut(data['Metascore'],bins=bins,labels=group_name)
print(data['Metascore'].unique())
movie_quality=LabelEncoder()
data['Metascore']=movie_quality.fit_transform(data['Metascore'])
print(data['Metascore'])
print(data['Metascore'].value_counts())
sns.countplot(data['Metascore'])
"""
Dividing the dataset
"""
X=data.drop('Metascore',axis=1)
y=data['Metascore']
"""
Train and test Data
"""
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)
"""
Random Forest Classifier
"""
print("Confusion Matrix and Accuracy for Random Forest")
rfc=RandomForestClassifier(n_estimators=200)
rfc.fit(X_train,y_train)
pred_rfc=rfc.predict(X_test)
print(confusion_matrix(y_test,pred_rfc))
accuracy=accuracy_score(y_test,pred_rfc)
print(accuracy)
"""
Support Vector Machine
"""
print("Confusion Matrix and Accuracy for SVM")
clf=svm.SVC()
clf.fit(X_train,y_train)
pred_clf=clf.predict(X_test)
print(confusion_matrix(y_test,pred_clf))
accuracy=accuracy_score(y_test,pred_clf)
print(accuracy)
"""
Neural Network Classifier
"""
print("Confusion Matrix and Accuracy for Neural Network")
nlpc=MLPClassifier(hidden_layer_sizes=(11,11,11),max_iter=500)
nlpc.fit(X_train,y_train)
pred_nlpc=nlpc.predict(X_test)
print(confusion_matrix(y_test,pred_nlpc))
accuracy=accuracy_score(y_test,pred_nlpc)
print(accuracy)
Exp-ANN,SVM,RFC
