Scribd
Upload
14 views

exp 4

Uploaded by

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

exp 4

Uploaded by

spoorthiitchanti
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Exercisestosolvetherealworldproblemsusingthefollowingmachinelearningmethods.a).

LinearRegression
b).LogisticRegression

Aim:
Tosolvethereal-worldproblemsusingthemachinelearningmethods.LinearRegressionand Logistic
Regression
Dataset: std_marks.csv constructed on own by using students lab internal and external marks.
Program code:
import pandas as pd
from sklearn import linear_model
import matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split
data=pd.read_csv(r"E:\sudhakar\std_marks.csv")
print('First 5 rows of the data set are:')
print(data.head())
dim=data.shape
print('Dimensions of the dataset are',dim)
print('Statistics of the data are:')
print(data.describe())
print('Correlation matrix of the dataset is:')
print(data.corr())
x_set=data[['internal']]
print('First5rowsoffeaturessetare:')
print(x_set.head())
y_set=data[['external']]
print('First5rowsoffeaturessetare:')
print(y_set.head())
x_train,x_test,y_train,y_test=train_test_split(x_set,y_set,test_size=0.3)
model=linear_model.LinearRegression()
model.fit(x_train,y_train)
print('Regression coefficient is',float(model.coef_))
print('Regression intercept is',float(model.intercept_))
y_pred=model.predict(x_test)
y_preds=[]
for i in y_pred:
y_preds.append(float(i))
print('Predicted values for test data are:')
print(y_preds)
print('mean squared error is ',mean_squared_error(y_test,y_pred))
plt.scatter(x_test,y_test,color='blue',label='actual y values')
plt.plot(x_test,y_pred,color='red',linewidth=3,label='predicted regression line')
plt.ylabel('y value')
plt.xlabel('x value')
plt.title('simple linear regression')
plt.legend(loc='best')
plt.show()
Outputscreenshots:
Exercise1b:
Program code:
import warnings
warnings.filterwarnings("ignore")
import pandas as pd
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import
LogisticRegression from sklearn.metrics import
confusion_matrix
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score
from sklearn.metrics import recall_score
from sklearn.metrics import precision_score
from sklearn.preprocessing import StandardScaler
data=pd.read_csv(r"E:\sudhakar\heart.csv")
print('The first 5 rows of the data set are:')
print(data.head())
dim=data.shape
print('Dimensions of the dataset are',dim)
print('Statistics of the data are:')
print(data.describe())
print('Correlation matrix of the dataset is:')
print(data.corr())
class_lbls=data['target'].unique()
class_labels=[]
for x in class_lbls:
class_labels.append(str(x))
print('Class labels are:')
print(class_labels)
sns.countplot(data['target'])
col_names=data.columns
feature_names=col_names[:-1]
feature_names=list(feature_names)
print('Feature names are:')
print(feature_names)
x_set = data.drop(['target'], axis=1)
print('First5rowsoffeaturessetare:')
print(x_set.head())
y_set=data[['target']]
print('First5rowsoffeaturessetare:')
print(y_set.head())
scaler=StandardScaler()
x_train,x_test,y_train, y_test=train_test_split(x_set,y_set,test_size=0.3)
scaler.fit(x_train)
x_train=scaler.transform(x_train)
model = LogisticRegression()
model.fit(x_train, y_train)
x_test=scaler.transform(x_test)
y_pred=model.predict(x_test)
print('Predicted class labels for test data are:')
print(y_pred)
print("Accuracy:",accuracy_score(y_test, y_pred))
print("Precision:",precision_score(y_test, y_pred))
print("Recall:",recall_score(y_test, y_pred))

print(classification_report(y_test,y_pred,target_names=class_labels))
cm=confusion_matrix(y_test,y_pred)
df_cm=pd.DataFrame(cm,columns=class_labels,index=class_labels)
df_cm.index.name = 'Actual'
df_cm.columns.name='Predicted's
ns.set(font_scale=1.5)
sns.heatmap(df_cm,annot=True,cmap="Blues",fmt='d')

Output screen shots:

You might also like