Scribd
Upload
11 views

Codes

The document shows code examples for several machine learning algorithms including SVM, SVC, Naive Bayes, KMeans clustering using elbow method and silhouette scores, PCA, and a confusion matrix. It includes code to load datasets, split data into training and test sets, train models, evaluate accuracy, and visualize results.

Uploaded by

Vamshi Krishna
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
11 views

Codes

The document shows code examples for several machine learning algorithms including SVM, SVC, Naive Bayes, KMeans clustering using elbow method and silhouette scores, PCA, and a confusion matrix. It includes code to load datasets, split data into training and test sets, train models, evaluate accuracy, and visualize results.

Uploaded by

Vamshi Krishna
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

1.

SVM
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn import svm
from sklearn import metrics

iris= datasets.load_iris()
print("Features: ", iris.feature_names)
print("Labels: ", iris.target_names)
print("Data Shape:" ,iris.data.shape)
print("Data samples:", iris.data[:5])
print("Target label:", iris.target)

X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target,


test_size=0.3,random_state=109)
clf = svm.SVC(kernel='linear')
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)

print("Accuracy:",metrics.accuracy_score(y_test, y_pred))
print("Precision:",metrics.precision_score(y_test, y_pred, average='weighted'))
print("Recall:",metrics.recall_score(y_test, y_pred, average='weighted'))

2. SVC
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import pandas as pd
dataset = pd.DataFrame({
'ID': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'Feature1': [0.5, 0.8, 0.3, 0.2, 0.6, 0.4, 0.7, 0.9, 0.1, 0.5],
'Feature2': [0.1, 0.2, 0.6, 0.9, 0.4, 0.3, 0.8, 0.7, 0.5, 0.6],
'Class': [0, 0, 1, 1, 1, 0, 1, 1, 0, 0]
})
target = dataset["Class"]
features = dataset.drop(["ID", "Class"], axis=1)
X_train,X_test,y_train,y_test =
train_test_split(features,target,test_size=0.2,random_state=10)

svc_model = SVC(C=.1, kernel='linear', gamma=1)


svc_model.fit(X_train, y_train)
prediction = svc_model .predict(X_test)

print(svc_model.score(X_train, y_train))
print(svc_model.score(X_test, y_test))

3. NAÏVE BYTES
from sklearn.datasets import load_iris
iris = load_iris()

# store the feature matrix (X) and response vector (y)


X = iris.data
y = iris.target

# splitting X and y into training and testing sets


from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4,
random_state=1)

# training the model on training set


from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
gnb.fit(X_train, y_train)

# making predictions on the testing set


y_pred = gnb.predict(X_test)

# comparing actual response values (y_test) with predicted response


values (y_pred)
from sklearn import metrics
print("Gaussian Naive Bayes model accuracy(in %):",
metrics.accuracy_score(y_test, y_pred)*100)

4. KMeans (Elbow method)


from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import pandas as pd

x=[10,20,56,85,41,36,2,5,59,6,3,2,4]
y=[5,9,6,3,5,2,5,4,15,25,63,52,87]
data=list(zip(x,y))
inertia=[]

for i in range(1,13):
kmeans=KMeans(n_clusters=i)
kmeans.fit(data)
inertia.append(kmeans.inertia_)

plt.plot(range(1,13),inertia,marker='o')
plt.title('Elbow method')
plt.xlabel('number of clusters')
plt.ylabel('inertias')
plt.show()
kmeans=KMeans(n_clusters=3)
kmeans.fit(data)
plt.scatter(x,y,c=kmeans.labels_)
plt.show()
5. KMeans(silht score)
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
from sklearn.metrics import silhouette_score
import pandas as pd

x=[10,20,56,85,41,36,2,5,59,6,3,2,4]
y=[5,9,6,3,5,2,5,4,15,25,63,52,87]
data=list(zip(x,y))
kmeans = KMeans(n_clusters=2)
kmeans.fit(data)
plt.scatter(x, y, c=kmeans.labels_)
plt.show()

score=silhouette_score(data, kmeans.labels_, metric='euclidean')


print('silhouette_score: %.3f' % score)

6. PCA
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns
from sklearn.datasets import load_breast_cancer
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA

cancer = load_breast_cancer()
cancer.keys()
print(cancer['DESCR'])
df = pd.DataFrame(cancer['data'],columns=cancer['feature_names'])
df.head()

Scaler = StandardScaler()
Scaler.fit(df)
scaled_data = Scaler.transform(df)

pca = PCA(n_components=2)
pca.fit(scaled_data)

x_pca = pca.transform(scaled_data)
scaled_data.shape
x_pca.shape

plt.figure(figsize=(8,6))
plt.scatter(x_pca[:,0],x_pca[:,1],c=cancer['target'],cmap='plasma')
plt.xlabel('First principal component')
plt.ylabel('Second Principal Component')

pca.components_
df_comp =
pd.DataFrame(pca.components_,columns=cancer['feature_names'])
plt.figure(figsize=(12,6))
sns.heatmap(df_comp,cmap='plasma',)

7. CONFUSION MATRIX
from sklearn.metrics._plot.confusion_matrix import confusion_matrix
#Import the necessary libraries
import numpy as np
from sklearn.metrics import confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt
actual = np.array(['Rain', 'No rain', 'Rain', 'No Rain', 'Rain', 'No Rain', 'Rain', 'No
Rain', 'No Rain', 'No Rain'])
predicted = np.array(['Rain', 'No Rain', 'Rain', 'No Rain', 'Rain', 'Rain', 'Rain',
'Rain', 'No Rain', 'No Rain'])
cm = confusion_matrix(actual,predicted)
sns.heatmap(cm,
annot=True,
fmt='g',
xticklabels=['Rain', 'No Rain'],
yticklabels=['Rain', 'No Rain'])
plt.ylabel('Prediction', fontsize=13)
plt.xlabel('Actual', fontsize=13)
plt.title('Confusion Matrix', fontsize=17)
plt.show()

8. DBSCAN

You might also like