Scribd
Upload
5 views7 pages

ML LAB .Simple

The document outlines a series of Python programming exercises focused on various statistical and machine learning techniques, including central tendency measures, linear regression, decision trees, KNN, logistic regression, and K-means clustering. Each week presents different libraries and methods, demonstrating practical implementations with sample datasets. The exercises utilize libraries such as NumPy, Pandas, and Scikit-learn to perform data analysis and model predictions.

Uploaded by

hasinipatel16
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
5 views7 pages

ML LAB .Simple

The document outlines a series of Python programming exercises focused on various statistical and machine learning techniques, including central tendency measures, linear regression, decision trees, KNN, logistic regression, and K-means clustering. Each week presents different libraries and methods, demonstrating practical implementations with sample datasets. The exercises utilize libraries such as NumPy, Pandas, and Scikit-learn to perform data analysis and model predictions.

Uploaded by

hasinipatel16
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

3/15/26, 9:42 PM ML_LAB

In [1]: #Week-1
# Write a python program to compute Central Tendency Measures: Mean, Median, Mod

import statistics as st
import numpy as np
d=[20,10,50,3,40,3,2]
print("Mean:",[Link](d))
print("Median:",[Link](d))
print("Mode:",[Link](d))
print("Variance:",[Link](d))
print("Standard deviation:",[Link](d))
print([Link](d))

Mean: 18.285714285714285
Median: 10
Mode: 3
Variance: 380.23809523809524
Standard deviation: 18.053209336484713
19.49969474730554

In [7]: # Week-2
#Study of Python Basic Libraries such as Statistics, Math, Numpy and Scipy

import statistics as st
import math as mp
import numpy as np
from scipy import stats
d=[1,2,3,4]
print("mean:",[Link](d))
print("mode:",[Link](d))
print("power:",[Link](3,2))
print("pi:",[Link])
print("root:",[Link](7))
print("SD:",[Link](d))
print("SD:",[Link](d))
print("variance:",[Link](d))

mean: 2.5
mode: 1
power: 9.0
pi: 3.141592653589793
root: 2.6457513110645907
SD: 1.118033988749895
SD: 1.2909944487358056
variance: 1.6666666666666667

In [5]: #Week-3
#Study of Python Libraries for ML application such as Pandas and Matplotlib

import pandas as pd
import [Link] as plt
df=[Link]({"marks":[50,60,90,80]})
[Link](kind="line")

[Link]("students")
[Link]("marks")
[Link]("marks graph")
[Link]()

[Link] 1/7
3/15/26, 9:42 PM ML_LAB

In [21]: #Week-4
#Write a Python program to implement Simple Linear Regression

import numpy as np

x=[Link]([1,3,5,7,13])
y=[Link]([2,4,6,7,8])
m=[Link](([Link]())*([Link]()))/[Link](([Link]())**2)
c=[Link]()-m*[Link]()

print("m=",m)
print("c=",c)

m= 0.47641509433962254
c= 2.6367924528301896

In [13]: #Week-5
#Implementation of Multiple Linear Regression for House Price Prediction using s
import numpy as np
import pandas as pd
import [Link] as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
data={
'area':[1000,1500,300,500,150],
'bedrooms':[2,3,6,8,3],
'age':[10,5,9,2,8],
'price':[50,75,1,5,8]
}
df=[Link](data)
print(df)

x=df[['area','bedrooms','age']]

[Link] 2/7
3/15/26, 9:42 PM ML_LAB

y=df['price']

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)

model=LinearRegression()

[Link](x_train,y_train)

predicted_price=[Link]([[200,4,3]])
print("predicted price:",predicted_price[0])

print("intercept:",model.intercept_)
print("coefficents:",model.coef_)

[Link](df['area'],df['price'])

[Link](200,predicted_price)
[Link]("Area")
[Link]("Price")
[Link]("House Price Prediction")

[Link]()

area bedrooms age price


0 1000 2 10 50
1 1500 3 5 75
2 300 6 9 1
3 500 8 2 5
4 150 3 8 8
predicted price: 12.16406249999983
intercept: 29.94791666666646
coefficents: [ 0.04630208 -5.63802083 -1.49739583]
C:\Users\Preethi\anaconda3\Lib\site-packages\sklearn\[Link]: UserWarning: X
does not have valid feature names, but LinearRegression was fitted with feature n
ames
[Link](

[Link] 3/7
3/15/26, 9:42 PM ML_LAB

In [15]: #Week-6
#Implementation of Decision tree using sklearn and its parameter tuning

from [Link] import load_iris


from [Link] import DecisionTreeClassifier
from sklearn.model_selection import train_test_split,GridSearchCV
from [Link] import accuracy_score
x,y=load_iris(return_X_y=True)
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)
model=DecisionTreeClassifier()
[Link](x_train,y_train)
pred=[Link](x_test)

print("accuracy:",accuracy_score(y_test,pred))

params={"max_depth":[2,3,4,5]}
grid=GridSearchCV(DecisionTreeClassifier(),params)
[Link](x_train,y_train)

best_model=grid.best_estimator_
best_pred=best_model.predict(x_test)

print("tuned accuracy :",accuracy_score(y_test,best_pred))

accuracy: 1.0
tuned accuracy : 1.0

In [45]: #Week-7
#Implementation of KNN using sklearn

import pandas as pd
from sklearn.model_selection import train_test_split

[Link] 4/7
3/15/26, 9:42 PM ML_LAB

from [Link] import KNeighborsRegressor


from [Link] import StandardScaler
from [Link] import mean_squared_error

data={
'area':[1000,1500,300,500,150],
'bedrooms':[2,3,6,8,3],
'price':[50,75,1,5,8]
}

df=[Link](data)
print(df)
x=df[['area','bedrooms']]
y=df['price']

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)

scaler=StandardScaler()
x_train=scaler.fit_transform(x_train)
x_test=[Link](x_test)

knn=KNeighborsRegressor(n_neighbors=3)
[Link](x_train,y_train)

y_pred=[Link](x_test)
print("predicted prices:",y_pred)

print("mse:",mean_squared_error(y_test,y_pred))

new_house=[Link]([[1400,3]])

print("predicted price:",[Link](new_house))

area bedrooms price


0 1000 2 50
1 1500 3 75
2 300 6 1
3 500 8 5
4 150 3 8
predicted prices: [28.]
mse: 484.0
predicted price: [28.]
C:\Users\Preethi\anaconda3\Lib\site-packages\sklearn\[Link]: UserWarning: X
does not have valid feature names, but StandardScaler was fitted with feature nam
es
[Link](

In [21]: #Week-8
#Implementation of Logistic Regression using sklearn

from [Link] import load_iris


from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from [Link] import accuracy_score

x,y=load_iris(return_X_y=True)

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)

model=LogisticRegression(max_iter=200)

[Link] 5/7
3/15/26, 9:42 PM ML_LAB

[Link](x_train,y_train)
y_pred=[Link](x_test)
print("accuracy:",accuracy_score(y_test,y_pred))

accuracy: 1.0

In [55]: # Week-9
# Implementation of K-Means Clustering

from [Link] import load_iris


from [Link] import KMeans
import [Link] as plt

iris = load_iris()
x = [Link]

kmeans = KMeans(n_clusters=3, random_state=42)


[Link](x)

labels = kmeans.labels_

print("cluster labels:\n", labels)


print("cluster centers:\n", kmeans.cluster_centers_)
print()

[Link](x[:,0], x[:,1], c=labels)

[Link]("feature 1")
[Link]("feature 2")

[Link]()

C:\Users\Preethi\anaconda3\Lib\site-packages\sklearn\cluster\_kmeans.py:1429: Use
rWarning: KMeans is known to have a memory leak on Windows with MKL, when there a
re less chunks than available threads. You can avoid it by setting the environmen
t variable OMP_NUM_THREADS=1.
[Link](
cluster labels:
[1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 0 2 0 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
2 2 2 0 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 0 2 0 0 0 0 2 0 0 0 0
0 0 2 2 0 0 0 0 2 0 2 0 2 0 0 2 2 0 0 0 0 0 2 0 0 0 0 2 0 0 0 2 0 0 0 2 0
0 2]
cluster centers:
[[6.85384615 3.07692308 5.71538462 2.05384615]
[5.006 3.428 1.462 0.246 ]
[5.88360656 2.74098361 4.38852459 1.43442623]]

[Link] 6/7
3/15/26, 9:42 PM ML_LAB

In [ ]:

[Link] 7/7

You might also like