LINEAR SVM
import pandas as pd
from sklearn.datasets import load_iris
iris=load_iris()
from sklearn.neighbors import KNeighborsClassifier
knn=KNeighborsClassifier(n_neighbors=10)
iris.feature_names
['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal
width (cm)']
iris.target_names
array(['setosa', 'versicolor', 'virginica'], dtype='<U10')
df=pd.DataFrame(iris.data,columns=iris.feature_names)
df.head
<bound method NDFrame.head of sepal length (cm) sepal width (cm) petal
length (cm) petal width (cm) 0 5.1 3.5 1.4 0.2 1 4.9 3.0 1.4 0.2 2 4.7
3.2 1.3 0.2 3 4.6 3.1 1.5 0.2 4 5.0 3.6 1.4 0.2 .. ... ... ... ... 145
6.7 3.0 5.2 2.3 146 6.3 2.5 5.0 1.9 147 6.5 3.0 5.2 2.0 148 6.2 3.4 5.4
2.3 149 5.9 3.0 5.1 1.8 [150 rows x 4 columns]>
df['target']=iris.target
df.head()
sepal length (cm)sepal width (cm)petal length (cm)petal width
(cm)target05.13.51.40.2014.93.01.40.2024.73.21.30.2034.63.11.50.2045.03.61.40.20
df[df.target==1].head()
sepal length (cm)sepal width (cm)petal length (cm)petal width
(cm)target507.03.24.71.41516.43.24.51.51526.93.14.91.51535.52.34.01.31546.52.84.61.51
df[df.target==2].head()
df['flower_name'] =df.target.apply(lambda x:
iris.target_names[x])
df.head()
df[45:55]
df0=df[:50]
df1=df[50:100]
df2=df[100:]
import matplotlib.pyplot as plt
%matplotlib inline
plt.xlabel('Sepal Length')
plt.ylabel('Sepal Width')
plt.scatter(df0['sepal length (cm)'],df0['sepal width
(cm)'],color="green",marker='+')
plt.scatter(df1['sepal length (cm)'],df1['sepal width
(cm)'],color="blue",marker='.')
NONLINEAR SVM
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
X = np.random.randn(100,2)
y = np.array([0]*50+[1]*50)
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.3, random_state=0)
scaler = StandardScaler()
classifier = SVC(kernel='rbf', gamma='scale')
classifier.fit(X_train, y_train)
plt.figure(figsize=(4, 3))
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
np.arange(y_min, y_max, 0.1))
z=classifier.predict(np.c_[xx.ravel(),yy.ravel()])
z=z.reshape(xx.shape)
plt.contourf(xx, yy,z,alpha=0.4)
plt.scatter(X[:, 0], X[:, 1], c=y, s=20, edgecolors='b')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.title('Non-linear SVM')
plt.show()
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets
iris = datasets.load_iris()
X = iris.data[:, :2]
y = iris.target
C = 1.0
svc = svm.SVC(kernel ='rbf', C = 1).fit(X, y)
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
h = (x_max / x_min)/100
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
plt.subplot(1, 1, 1)
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets
iris = datasets.load_iris()
X = iris.data[:, :2]
y = iris.target
C = 1.0
svc = svm.SVC(kernel ='rbf', C = 1).fit(X, y)
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
h = (x_max / x_min)/100
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
plt.subplot(1, 1, 1)
Z = svc.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, cmap = plt.cm.Paired, alpha = 0.8)
plt.scatter(X[:, 0], X[:, 1], c = y, cmap = plt.cm.Paired)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.title('SVC with non-linear kernel')
plt.show()
KNN
import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.neighbors import KNeighborsClassifier
cmap = ListedColormap(['#FF0000','#00FF00','#0000FF'])
iris = datasets.load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=1234)
h=0.02
plt.figure()
plt.scatter(X[:,2],X[:,3], c=y, cmap=cmap, edgecolor='k',
s=50)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.show()
clf = KNeighborsClassifier(n_neighbors=5)
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)
print(predictions)
acc = np.sum(predictions == y_test) / len(y_test)
print(acc)
PCA
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
data=pd.read_csv("/content/Acoustic Features - Acoustic
Features.csv")
x=data.iloc[:,5:9].values
y=data.iloc[:,0].values
X_train, X_test, y_train, y_test = train_test_split(x, y,
test_size = 0.2, random_state = 0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
pca = PCA(n_components = 3)
principalComponents = pca.fit_transform(x)
principalDf = pd.DataFrame(data = principalComponents, columns
= ['PC 1', 'PC 2','PC 3'])
finalDf = pd.concat([principalDf, data[['Class']]], axis = 1)
fig = plt.figure(figsize = (8,8))
ax = fig.add_subplot(1,1,1)
ax.set_xlabel('PC 1')
ax.set_ylabel('PC 2')
targets = ['relax', 'happy', 'sad', 'angry']
colors = ['g', 'y', 'b','r']
for target, color in zip(targets,colors):
ind = finalDf['Class'] == target
ax.scatter(finalDf.loc[ind, 'PC 1'], finalDf.loc[ind, 'PC
2'],c = color, s = 10)
ax.legend(targets)
ax.grid
K MEANS
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset= pd.read_csv("/content/Acoustic Features.csv")
X=dataset.iloc[:, [1,4]].values
from sklearn.cluster import KMeans
wcss=[]
for i in range(1,11):
kmeans = KMeans(n_clusters=i, init ='k-means++',
max_iter=300, n_init=10,random_state=0 )
kmeans.fit(X)
wcss.append(kmeans.inertia_)
plt.plot(range(0,10),wcss)
plt.title('The Elbow Method Graph')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()
kmeans = KMeans(n_clusters=5, init ='k-means++', max_iter=300,
n_init=5,random_state=0 )
y_kmeans = kmeans.fit_predict(X)
plt.scatter(X[y_kmeans==0, 0], X[y_kmeans==0, 1], s=10,
c='red', label ='Cluster 1')
plt.scatter(X[y_kmeans==1, 0], X[y_kmeans==1, 1], s=10,
c='blue', label ='Cluster 2')
plt.scatter(X[y_kmeans==2, 0], X[y_kmeans==2, 1], s=10,
c='green', label ='Cluster 3')
plt.scatter(X[y_kmeans==3, 0], X[y_kmeans==3, 1], s=10,
c='cyan', label ='Cluster 4')
plt.scatter(X[y_kmeans==4, 0], X[y_kmeans==4, 1], s=10,
c='magenta', label ='Cluster 5')
plt.scatter(kmeans.cluster_centers_[:, 0],
kmeans.cluster_centers_[:, 1], s=30, c='yellow', label =
'Centroids')
plt.xlabel('Energy mean')
plt.ylabel('Class')
plt.show()
LINKAGE
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
ourData = pd.read_csv('/content/Mall_Cust.csv')
ourData.head()
newData = ourData.iloc[:, [2, 3]].values
import scipy.cluster.hierarchy as sch
dendrogram = sch.dendrogram(sch.linkage(newData, method =
'single'))
plt.title('Dendrogram')
plt.xlabel('Customers')
plt.ylabel('Euclidean distances')
plt.show()
import numpy as np
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import dendrogram, linkage
x = [4, 5, 10, 4, 3, 11, 14 , 6, 10, 12]
y = [21, 19, 24, 17, 16, 25, 24, 22, 21, 21]
data = list(zip(x, y))
linkage_data = linkage(data, method='complete',
metric='euclidean')
dendrogram(linkage_data)
plt.show()
