Scribd
Upload
29 views9 pages

Machine Learning Experiments Overview

The document contains multiple Python experiments focusing on different machine learning techniques, including hypothesis generation, linear regression, logistic regression, and model evaluation. It demonstrates data loading, preprocessing, model training, and performance metrics calculation using libraries such as pandas, numpy, and scikit-learn. Each experiment showcases specific algorithms and methods for analyzing datasets, including candidate elimination, linear regression, and classification metrics.

Uploaded by

sushmasri.keerthi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
29 views9 pages

Machine Learning Experiments Overview

The document contains multiple Python experiments focusing on different machine learning techniques, including hypothesis generation, linear regression, logistic regression, and model evaluation. It demonstrates data loading, preprocessing, model training, and performance metrics calculation using libraries such as pandas, numpy, and scikit-learn. Each experiment showcases specific algorithms and methods for analyzing datasets, including candidate elimination, linear regression, and classification metrics.

Uploaded by

sushmasri.keerthi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Exp-1

import csv
a = []
with open('/content/sample_data/[Link]','r')as csvfile:
for row in [Link](csvfile): n
[Link](row)
print(a)
print("\n The total number of training instances are : ",len(a))
num_attribute = len(a[0])-1
num_attribute
print("\n The initial hypothesis is : ")
hypothesis = ['0'] * num_attribute
print(hypothesis)
for i in range(0,len(a)):
if a[i][num_attribute] == 'yes':
for j in range(0,num_attribute):
if hypothesis[j] == '0' or hypothesis[j] == a[i][j]:
hypothesis[j] = a[i][j]
else:
hypothesis[j] = '?'
print("\n The hypothesis for the training instance {} is
:\n".format(i+1),hypothesis)
print("\n The Maximum Specific hypothesis for the training instance is
: ")
print(hypothesis)

Exp-2
import numpy as np
import pandas as p
data=[Link](data=pd.read_csv('/content/[Link]'))
concepts=[Link]([Link][:,:-1])
print(concepts)
target=[Link]([Link][:,-1])
print(target)
def learn(concepts, target):
specific_h = concepts[0].copy()
print("initialization of specific_h and general_h")
print(specific_h)
general_h = [["?" for i in range(len(specific_h))] for i in
range(len(specific_h))]
print(general_h)
for i, h in enumerate(concepts):
if target[i] == "yes":
for x in range(len(specific_h)):
if h[x] != specific_h[x]:
specific_h[x] = '?'
general_h[x][x] = '?'
# print(specific_h)
if target[i] == "no":
for x in range(len(specific_h)):
if h[x] != specific_h[x]:
general_h[x][x] = specific_h[x]
else:
general_h[x][x] = '?'
print("steps of Candidate Elimination Algorithm", i + 1)
print(specific_h)
print(general_h)
indices = [i for i, val in enumerate(general_h) if val == ['?',
'?', '?', '?', '?', '?']]
for i in indices:
general_h.remove(['?', '?', '?', '?', '?', '?'])
return specific_h, general_h
s_final, g_final = learn(concepts, target)
print("Final Specific_h:", s_final, sep="\n")
print("Final General_h:", g_final, sep="\n")

Exp-4a
import pandas as pd
import [Link] as plt
import numpy as np
%matplotlib inline
df=pd.read_csv('/content/sample_data/[Link]')
[Link]()
[Link](df['Height'],df['Weight'])
[Link]("Height")
[Link]("Weight")
[Link]()
import seaborn as sns
[Link](df)
x=df[['Height']]
y=df[['Weight']]

x_series=df['Height']
[Link](x_series).shape
[Link](y).shape
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.25,rando
m_state=42)
from [Link] import StandardScaler
scaler=StandardScaler()
x_train=scaler.fit_transform(x_train)
x_test=[Link](x_test)
x_test
from sklearn.linear_model import LinearRegression
regression=LinearRegression(n_jobs = -1)
[Link](x_train,y_train)
print("Coefficient or slope:",regression.coef_)
print("Intercept:",regression.intercept_)
[Link](x_train,y_train)
[Link](x_train,[Link](x_train))
y_pred = [Link]
from [Link] import mean_absolute_error,mean_squared_error
mse=mean_squared_error(y_test,y_pred)
mae=mean_absolute_error(y_test,y_pred)
rmse=[Link](mse)
print(mse)
print(mae)
print(rmse)

Exp-4b
import seaborn as sns
import pandas as pd
import numpy as np
df=sns.load_dataset('iris')
[Link]()
df['species'].unique()
[Link]().sum()
df = df[df['species']!= 'setosa']
[Link]()
df['species']= df['species'].map({'versicolor': 0, 'virginica':1})
[Link]()
[Link] (df, hue='species')
[Link]()
X = [Link][:, -1]
y= [Link][:, -1]
X
y
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y, test_size=0.2,
random_state=2)
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()

from sklearn.model_selection import GridSearchCV


# Adjusted param_grid
parameter = {
'penalty': ['l2'], # Use only 'l2' penalty for 'lbfgs' solver
'C':[1,2,3,4,5,6,10, 20, 30, 40, 50, 100],
'max_iter': [100, 200, 300],
'solver': ['lbfgs', 'liblinear', 'newton-cg', 'sag', 'saga'] #
Explore other solvers
}
classifier_regression = GridSearchCV(classifier, param_grid=parameter,
scoring='accuracy', cv=5)
classifier_regression.fit(X_train, y_train)
print(classifier_regression.best_params_)
print(classifier_regression.best_score_)
y_pred = classifier_regression.predict(X_test)
from [Link] import accuracy_score,classification_report
score=accuracy_score(y_pred,y_test)
print(score)
print(classification_report(y_pred,y_test))

Exp-4c
import [Link] as plt
from [Link] import load_breast_cancer
dataset=load_breast_cancer(as_frame=True)
dataset['target'].value_counts()
x=dataset['data']
y=dataset['target']
y
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random
_state=0)
from [Link] import StandardScaler
sc=StandardScaler()
x_train=sc.fit_transform(x_train)
models={}
ss_test=StandardScaler()
x_test=ss_test.fit_transform(x_test)
from [Link] import confusion_matrix
cm = confusion_matrix(y_test, predictions).ravel()
TN,FP,FN,TP=confusion_matrix(y_test,predictions).ravel()
print('True Positive(TP) = ',TP)
print('False Positive(FP) = ',FP)
print('True Negative(TN) = ',TN)
print('False Negative(FN) = ',FN)
accuracy = (TP+TN)/(TP+FP+TN+FN)
print('Accuracy of BinaryClassifier ={:0.3f}'.format(accuracy))
models={}
from sklearn.linear_model import LogisticRegression
models['Logistic Regression'] = LogisticRegression()
from [Link] import LinearSVC
models['Support Vector Classifier'] = LinearSVC()
from [Link] import DecisionTreeClassifier
models['Decision Tree Classifier'] = DecisionTreeClassifier()
from [Link] import RandomForestClassifier
models['Random Forest Classifier'] = RandomForestClassifier()
from sklearn.naive_bayes import GaussianNB
models['Naive Bayes Classifier'] = GaussianNB()
from [Link] import KNeighborsClassifier
models['K Nearest Neighbor Classifier'] = KNeighborsClassifier()
from [Link] import accuracy_score,precision_score,recall_score
accuracy,precision,recall={},{},{}
for key in [Link]():
models[key].fit(x_train,y_train)
predictions = models[key].predict(x_test)
accuracy[key] = accuracy_score(y_test,predictions)
precision[key] = precision_score(y_test,predictions)
recall[key] = recall_score(y_test,predictions)
import pandas as pd
df_model=[Link](index=[Link](),columns=['Accuracy','Precisio
n','Recall'])
df_model['Accuracy']=list([Link]())
df_model['Precision']=list([Link]())
df_model['Recall']=list([Link]())
df_model
ax=df_model.[Link]()
[Link](ncol=len([Link]()),bbox_to_anchor=(0,1),loc='lower
left',prop={'size':10})
plt.tight_layout()
[Link]()
Exp_1
import csv
a = []
with open('/content/sample_data/[Link]','r')as csvfile:
for row in [Link](csvfile): n
[Link](row)
print(a)
print("\n The total number of training instances are : ",len(a))
num_attribute = len(a[0])-1
num_attribute
print("\n The initial hypothesis is : ")
hypothesis = ['0'] * num_attribute
print(hypothesis)
for i in range(0,len(a)):
if a[i][num_attribute] == 'yes':
for j in range(0,num_attribute):
if hypothesis[j] == '0' or hypothesis[j] == a[i][j]:
hypothesis[j] = a[i][j]
else:
hypothesis[j] = '?'
print("\n The hypothesis for the training instance {} is :\n".format(i+1),hypothesis)
print("\n The Maximum Specific hypothesis for the training instance is : ")
print(hypothesis)

Exp-2
import numpy as np
import pandas as pd
data=[Link](data=pd.read_csv('/content/[Link]'))
concepts=[Link]([Link][:,:-1])
print(concepts)
target=[Link]([Link][:,-1])
print(target)
def learn(concepts, target):
specific_h = concepts[0].copy()
print("initialization of specific_h and general_h")
print(specific_h)
general_h = [["?" for i in range(len(specific_h))] for i in range(len(specific_h))]
print(general_h)
for i, h in enumerate(concepts):
if target[i] == "yes":
for x in range(len(specific_h)):
if h[x] != specific_h[x]:
specific_h[x] = '?'
general_h[x][x] = '?'
if target[i] == "no":
for x in range(len(specific_h)):
if h[x] != specific_h[x]:
general_h[x][x] = specific_h[x]
else:
general_h[x][x] = '?'
print("steps of Candidate Elimination Algorithm", i + 1)
print(specific_h)
print(general_h)
indices = [i for i, val in enumerate(general_h) if val == ['?', '?', '?', '?', '?', '?']]
for i in indices:
general_h.remove(['?', '?', '?', '?', '?', '?'])
return specific_h, general_h
s_final, g_final = learn(concepts, target)
print("Final Specific_h:", s_final, sep="\n")
print("Final General_h:", g_final, sep="\n")

EXP-3
import pandas as pd
import [Link] as plt
import numpy as np
%matplotlib inline
df=pd.read_csv('/content/sample_data/[Link]')
[Link]()
[Link](df['Height'],df['Weight'])
[Link]("Height")
[Link]("Weight")
[Link]()
import seaborn as sns
[Link](df)
x=df[['Height']]
y=df[['Weight']]
x_series=df['Height']
[Link](x_series).shape
[Link](y).shape
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.25,random_state=42)
from [Link] import StandardScaler
scaler=StandardScaler()
x_train=scaler.fit_transform(x_train)
x_test=[Link](x_test)
x_test
from sklearn.linear_model import LinearRegression
regression=LinearRegression(n_jobs = -1)
[Link](x_train,y_train)
print("Coefficient or slope:",regression.coef_)
print("Intercept:",regression.intercept_)
[Link](x_train,y_train)
[Link](x_train,[Link](x_train))

y_pred = [Link]
y_pred = [Link](x_test)
from [Link] import mean_absolute_error,mean_squared_error
mse=mean_squared_error(y_test,y_pred)
mae=mean_absolute_error(y_test,y_pred)
rmse=[Link](mse)
print(mse)
print(mae)
print(rmse)
EXP-4b
import seaborn as sns
import pandas as pd
import numpy as np
df=sns.load_dataset('iris')
[Link]()
df['species'].unique()
[Link]().sum()
df = df[df['species']!= 'setosa']
[Link]()
df['species']= df['species'].map({'versicolor': 0, 'virginica':1})
[Link]()
[Link] (df, hue='species')
[Link]()
X = [Link][:, -1]
y= [Link][:, -1]
X
y

from sklearn.model_selection import train_test_split


X_train,X_test,y_train,y_test = train_test_split(X,y, test_size=0.2, random_state=2)
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()

from sklearn.model_selection import GridSearchCV


parameter = {
'penalty': ['l2'], # Use only 'l2' penalty for 'lbfgs' solver
'C':[1,2,3,4,5,6,10, 20, 30, 40, 50, 100],
'max_iter': [100, 200, 300],
'solver': ['lbfgs', 'liblinear', 'newton-cg', 'sag', 'saga']
}
classifier_regression = GridSearchCV(classifier, param_grid=parameter, scoring='accuracy', cv=5)
classifier_regression.fit(X_train, y_train)
print(classifier_regression.best_params_)
print(classifier_regression.best_score_)
y_pred = classifier_regression.predict(X_test)
from [Link] import accuracy_score,classification_report
score=accuracy_score(y_pred,y_test)
print(score)
print(classification_report(y_pred,y_test))
EXP-4c

import [Link] as plt


from [Link] import load_breast_cancer

dataset=load_breast_cancer(as_frame=True)
dataset['target'].value_counts()
x=dataset['data']
y=dataset['target']
y
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)
from [Link] import StandardScaler
sc=StandardScaler()
x_train=sc.fit_transform(x_train)
models={}
ss_test=StandardScaler()
x_test=ss_test.fit_transform(x_test)
from [Link] import confusion_matrix
cm = confusion_matrix(y_test, predictions).ravel()
TN,FP,FN,TP=confusion_matrix(y_test,predictions).ravel()
print('True Positive(TP) = ',TP)
print('False Positive(FP) = ',FP)
print('True Negative(TN) = ',TN)
print('False Negative(FN) = ',FN)
accuracy = (TP+TN)/(TP+FP+TN+FN)
print('Accuracy of BinaryClassifier ={:0.3f}'.format(accuracy))
models={}
from sklearn.linear_model import LogisticRegression
models['Logistic Regression'] = LogisticRegression()

from [Link] import LinearSVC


models['Support Vector Classifier'] = LinearSVC()
from [Link] import DecisionTreeClassifier
models['Decision Tree Classifier'] = DecisionTreeClassifier()
from [Link] import RandomForestClassifier
models['Random Forest Classifier'] = RandomForestClassifier()
from sklearn.naive_bayes import GaussianNB
models['Naive Bayes Classifier'] = GaussianNB()
from [Link] import KNeighborsClassifier
models['K Nearest Neighbor Classifier'] = KNeighborsClassifier()
from [Link] import accuracy_score,precision_score,recall_score
accuracy,precision,recall={},{},{}
for key in [Link]():
models[key].fit(x_train,y_train)
predictions = models[key].predict(x_test)
accuracy[key] = accuracy_score(y_test,predictions)
precision[key] = precision_score(y_test,predictions)
recall[key] = recall_score(y_test,predictions)
import pandas as pd
df_model=[Link](index=[Link](),columns=['Accuracy','Precision','Recall'])
df_model['Accuracy']=list([Link]())
df_model['Precision']=list([Link]())
df_model['Recall']=list([Link]())
df_model
ax=df_model.[Link]()
[Link](ncol=len([Link]()),bbox_to_anchor=(0,1),loc='lower left',prop={'size':10})
plt.tight_layout()
[Link]()

EXP 5
pip install mlxtend
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from [Link] import bias_variance_decomp
url = '[Link]
dataframe = pd.read_csv(url, header=None)
[Link]()
data=[Link]
x=data[:,:-1]
y=data[:,-1]
y
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.33,random_state=1)
model=LinearRegression()
mse, bias, var = bias_variance_decomp(model, x_train, y_train, x_test, y_test, loss='mse', num_rounds=200, random_seed=1)
print('MSE : %.3f' % mse)
print('BIAS : %.3f' % bias)
print('VARIANCE : %.3f' % var)
sample_list=[11,13,15,16,13,16,11,15,17]
print("The list is : " + str(sample_list))
result=[]
for i in sample_list:
if i not in result:
[Link](i)
print("The list after removing duplicates : " + str(result))
from [Link] import load_iris
from sklearn.model_selection import cross_val_score,KFold
from sklearn.linear_model import LogisticRegression
iris = load_iris()
x = [Link]
y = [Link]
logreg = LogisticRegression()
kf=KFold(n_splits=5)
score = cross_val_score(logreg, x,y,cv=kf)
print("cross validation score are : {}" . format(score))
print("Average cross validation score are : {}" . format([Link]()))
Exp8
from sklearn.model_selection import train_test_split
from [Link] import KNeighborsClassifier
from [Link] import accuracy_score,confusion_matrix,classification_report
from sklearn import datasets
iris = datasets.load_iris()
x = [Link]
y = [Link]
print('sepal_length', 'sepal_width', 'petal_length', 'petal_width')
print(x)
print('class: 0-Iris-Setosa, 1-Iris-Versicolour, 2-Iris-Virginica')
print(y)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3)
classifier = KNeighborsClassifier(n_neighbors=3)
[Link](x_train, y_train)
y_pred = [Link](x_test)
y_pred
print('Confusion_Matrix')
print(confusion_matrix(y_test, y_pred))
print('Accuracy Metrics')
print(classification_report(y_test, y_pred))
EXP9
import numpy as np
import [Link] as plt
def generate_data():
[Link](42)
x = [Link](0, 10, 100)
y = [Link](x) + [Link](scale=0.1, size=[Link])
return x, y
def gaussian_weight(x,X,tau):
return [Link](-((X-x)**2)/(2*tau**2))
def locally_weighted_regression(X_train, y_train, x_query, tau):
w = [Link](gaussian_weight(x_query, X_train, tau))
X_bias = np.c_[[Link](X_train.shape[0]), X_train]
theta = [Link](X_bias.T @ w @ X_bias) @ X_bias.T @ w @ y_train
return [Link]([1, x_query]) @ theta
def predict(x_train,y_train,x_query,tau):
return [Link]([locally_weighted_regression(x_train,y_train,x,tau) for x in x_test])
X, y = generate_data()
tau = 0.5
x_test = [Link](0, 10, 100)
y_pred = predict(X, y, x_test, tau)
[Link](X, y, label="Training data", color="blue", alpha=0.5)
[Link](x_test, y_pred, label=f"LWR (tau={tau})", color="red", linewidth=2)
[Link]("x")
[Link]("y")
[Link]()
[Link]("Locally Weighted Regression")
[Link]()
Exp_1
import csv
a = []
with open('/content/sample_data/[Link]','r')as csvfile:
for row in [Link](csvfile): n
[Link](row)
print(a)
print("\n The total number of training instances are : ",len(a))
num_attribute = len(a[0])-1
num_attribute
print("\n The initial hypothesis is : ")
hypothesis = ['0'] * num_attribute
print(hypothesis)
for i in range(0,len(a)):
if a[i][num_attribute] == 'yes':
for j in range(0,num_attribute):
if hypothesis[j] == '0' or hypothesis[j] == a[i][j]:
hypothesis[j] = a[i][j]
else:
hypothesis[j] = '?'
print("\n The hypothesis for the training instance {} is :\n".format(i+1),hypothesis)
print("\n The Maximum Specific hypothesis for the training instance is : ")
print(hypothesis)

Exp-2
import numpy as np
import pandas as pd
data=[Link](data=pd.read_csv('/content/[Link]'))
concepts=[Link]([Link][:,:-1])
print(concepts)
target=[Link]([Link][:,-1])
print(target)
def learn(concepts, target):
specific_h = concepts[0].copy()
print("initialization of specific_h and general_h")
print(specific_h)
general_h = [["?" for i in range(len(specific_h))] for i in range(len(specific_h))]
print(general_h)
for i, h in enumerate(concepts):
if target[i] == "yes":
for x in range(len(specific_h)):
if h[x] != specific_h[x]:
specific_h[x] = '?'
general_h[x][x] = '?'
if target[i] == "no":
for x in range(len(specific_h)):
if h[x] != specific_h[x]:
general_h[x][x] = specific_h[x]
else:
general_h[x][x] = '?'
print("steps of Candidate Elimination Algorithm", i + 1)
print(specific_h)
print(general_h)
indices = [i for i, val in enumerate(general_h) if val == ['?', '?', '?', '?', '?', '?']]
for i in indices:
general_h.remove(['?', '?', '?', '?', '?', '?'])
return specific_h, general_h
s_final, g_final = learn(concepts, target)
print("Final Specific_h:", s_final, sep="\n")
print("Final General_h:", g_final, sep="\n")

EXP-3
import pandas as pd
import [Link] as plt
import numpy as np
%matplotlib inline
df=pd.read_csv('/content/sample_data/[Link]')
[Link]()
[Link](df['Height'],df['Weight'])
[Link]("Height")
[Link]("Weight")
[Link]()
import seaborn as sns
[Link](df)
x=df[['Height']]
y=df[['Weight']]
x_series=df['Height']
[Link](x_series).shape
[Link](y).shape
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.25,random_state=42)
from [Link] import StandardScaler
scaler=StandardScaler()
x_train=scaler.fit_transform(x_train)
x_test=[Link](x_test)
x_test
from sklearn.linear_model import LinearRegression
regression=LinearRegression(n_jobs = -1)
[Link](x_train,y_train)
print("Coefficient or slope:",regression.coef_)
print("Intercept:",regression.intercept_)
[Link](x_train,y_train)
[Link](x_train,[Link](x_train))

y_pred = [Link]
y_pred = [Link](x_test)
from [Link] import mean_absolute_error,mean_squared_error
mse=mean_squared_error(y_test,y_pred)
mae=mean_absolute_error(y_test,y_pred)
rmse=[Link](mse)
print(mse)
print(mae)
print(rmse)
EXP-4b
import seaborn as sns
import pandas as pd
import numpy as np
df=sns.load_dataset('iris')
[Link]()
df['species'].unique()
[Link]().sum()
df = df[df['species']!= 'setosa']
[Link]()
df['species']= df['species'].map({'versicolor': 0, 'virginica':1})
[Link]()
[Link] (df, hue='species')
[Link]()
X = [Link][:, -1]
y= [Link][:, -1]
X
y

from sklearn.model_selection import train_test_split


X_train,X_test,y_train,y_test = train_test_split(X,y, test_size=0.2, random_state=2)
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()

from sklearn.model_selection import GridSearchCV


parameter = {
'penalty': ['l2'], # Use only 'l2' penalty for 'lbfgs' solver
'C':[1,2,3,4,5,6,10, 20, 30, 40, 50, 100],
'max_iter': [100, 200, 300],
'solver': ['lbfgs', 'liblinear', 'newton-cg', 'sag', 'saga']
}
classifier_regression = GridSearchCV(classifier, param_grid=parameter, scoring='accuracy', cv=5)
classifier_regression.fit(X_train, y_train)
print(classifier_regression.best_params_)
print(classifier_regression.best_score_)
y_pred = classifier_regression.predict(X_test)
from [Link] import accuracy_score,classification_report
score=accuracy_score(y_pred,y_test)
print(score)
print(classification_report(y_pred,y_test))
EXP-4c

import [Link] as plt


from [Link] import load_breast_cancer

dataset=load_breast_cancer(as_frame=True)
dataset['target'].value_counts()
x=dataset['data']
y=dataset['target']
y
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)
from [Link] import StandardScaler
sc=StandardScaler()
x_train=sc.fit_transform(x_train)
models={}
ss_test=StandardScaler()
x_test=ss_test.fit_transform(x_test)
from [Link] import confusion_matrix
cm = confusion_matrix(y_test, predictions).ravel()
TN,FP,FN,TP=confusion_matrix(y_test,predictions).ravel()
print('True Positive(TP) = ',TP)
print('False Positive(FP) = ',FP)
print('True Negative(TN) = ',TN)
print('False Negative(FN) = ',FN)
accuracy = (TP+TN)/(TP+FP+TN+FN)
print('Accuracy of BinaryClassifier ={:0.3f}'.format(accuracy))
models={}
from sklearn.linear_model import LogisticRegression
models['Logistic Regression'] = LogisticRegression()

from [Link] import LinearSVC


models['Support Vector Classifier'] = LinearSVC()
from [Link] import DecisionTreeClassifier
models['Decision Tree Classifier'] = DecisionTreeClassifier()
from [Link] import RandomForestClassifier
models['Random Forest Classifier'] = RandomForestClassifier()
from sklearn.naive_bayes import GaussianNB
models['Naive Bayes Classifier'] = GaussianNB()
from [Link] import KNeighborsClassifier
models['K Nearest Neighbor Classifier'] = KNeighborsClassifier()
from [Link] import accuracy_score,precision_score,recall_score
accuracy,precision,recall={},{},{}
for key in [Link]():
models[key].fit(x_train,y_train)
predictions = models[key].predict(x_test)
accuracy[key] = accuracy_score(y_test,predictions)
precision[key] = precision_score(y_test,predictions)
recall[key] = recall_score(y_test,predictions)
import pandas as pd
df_model=[Link](index=[Link](),columns=['Accuracy','Precision','Recall'])
df_model['Accuracy']=list([Link]())
df_model['Precision']=list([Link]())
df_model['Recall']=list([Link]())
df_model
ax=df_model.[Link]()
[Link](ncol=len([Link]()),bbox_to_anchor=(0,1),loc='lower left',prop={'size':10})
plt.tight_layout()
[Link]()

EXP 5
pip install mlxtend
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from [Link] import bias_variance_decomp
url = '[Link]
dataframe = pd.read_csv(url, header=None)
[Link]()
data=[Link]
x=data[:,:-1]
y=data[:,-1]
y
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.33,random_state=1)
model=LinearRegression()
mse, bias, var = bias_variance_decomp(model, x_train, y_train, x_test, y_test, loss='mse', num_rounds=200, random_seed=1)
print('MSE : %.3f' % mse)
print('BIAS : %.3f' % bias)
print('VARIANCE : %.3f' % var)
sample_list=[11,13,15,16,13,16,11,15,17]
print("The list is : " + str(sample_list))
result=[]
for i in sample_list:
if i not in result:
[Link](i)
print("The list after removing duplicates : " + str(result))
from [Link] import load_iris
from sklearn.model_selection import cross_val_score,KFold
from sklearn.linear_model import LogisticRegression
iris = load_iris()
x = [Link]
y = [Link]
logreg = LogisticRegression()
kf=KFold(n_splits=5)
score = cross_val_score(logreg, x,y,cv=kf)
print("cross validation score are : {}" . format(score))
print("Average cross validation score are : {}" . format([Link]()))
Exp8
from sklearn.model_selection import train_test_split
from [Link] import KNeighborsClassifier
from [Link] import accuracy_score,confusion_matrix,classification_report
from sklearn import datasets
iris = datasets.load_iris()
x = [Link]
y = [Link]
print('sepal_length', 'sepal_width', 'petal_length', 'petal_width')
print(x)
print('class: 0-Iris-Setosa, 1-Iris-Versicolour, 2-Iris-Virginica')
print(y)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3)
classifier = KNeighborsClassifier(n_neighbors=3)
[Link](x_train, y_train)
y_pred = [Link](x_test)
y_pred
print('Confusion_Matrix')
print(confusion_matrix(y_test, y_pred))
print('Accuracy Metrics')
print(classification_report(y_test, y_pred))
EXP9
import numpy as np
import [Link] as plt
def generate_data():
[Link](42)
x = [Link](0, 10, 100)
y = [Link](x) + [Link](scale=0.1, size=[Link])
return x, y
def gaussian_weight(x,X,tau):
return [Link](-((X-x)**2)/(2*tau**2))
def locally_weighted_regression(X_train, y_train, x_query, tau):
w = [Link](gaussian_weight(x_query, X_train, tau))
X_bias = np.c_[[Link](X_train.shape[0]), X_train]
theta = [Link](X_bias.T @ w @ X_bias) @ X_bias.T @ w @ y_train
return [Link]([1, x_query]) @ theta
def predict(x_train,y_train,x_query,tau):
return [Link]([locally_weighted_regression(x_train,y_train,x,tau) for x in x_test])
X, y = generate_data()
tau = 0.5
x_test = [Link](0, 10, 100)
y_pred = predict(X, y, x_test, tau)
[Link](X, y, label="Training data", color="blue", alpha=0.5)
[Link](x_test, y_pred, label=f"LWR (tau={tau})", color="red", linewidth=2)
[Link]("x")
[Link]("y")
[Link]()
[Link]("Locally Weighted Regression")
[Link]()

You might also like