12/22/23, 3:45 AM practice

In [83]: import pandas as pd

import numpy as np
data = pd.read_csv("mbasalary.csv")
data.head()
#data.iloc[:,0:1]

Out[83]: S. No. Percentage in Grade 10 Salary

0 1 62.00 270000

1 2 76.33 200000

2 3 72.00 240000

3 4 60.00 250000

4 5 61.00 180000

In [84]: data = data[['Percentage in Grade 10','Salary']]

x = data[['Percentage in Grade 10']]
y= data[['Salary']]
data.describe()

Out[84]: Percentage in Grade 10 Salary

count 50.000000 50.000000

mean 63.922400 258192.000000

std 9.859937 76715.790993

min 37.330000 120000.000000

25% 57.685000 204500.000000

50% 64.700000 250000.000000

75% 70.000000 300000.000000

max 83.000000 450000.000000

In [85]: import matplotlib.pyplot as plt

plt.scatter(data.iloc[:,0:1],data.iloc[:,-1])

<matplotlib.collections.PathCollection at 0x26fcab243d0>
Out[85]:

localhost:8888/nbconvert/html/practice .ipynb?download=false 1/9

12/22/23, 3:45 AM practice

In [ ]:

In [ ]:

In [86]: data.mean()

Percentage in Grade 10 63.9224

Out[86]:
Salary 258192.0000
dtype: float64

In [87]: data.mode()

Out[87]: Percentage in Grade 10 Salary

0 68.0 300000

In [88]: data.median()

Percentage in Grade 10 64.7

Out[88]:
Salary 250000.0
dtype: float64

In [89]: data.std()

Percentage in Grade 10 9.859937

Out[89]:
Salary 76715.790993
dtype: float64

In [90]: data.quantile() #by default q=0.5

Percentage in Grade 10 64.7

Out[90]:
Salary 250000.0
Name: 0.5, dtype: float64

In [91]: data.quantile(q=0.25)

localhost:8888/nbconvert/html/practice .ipynb?download=false 2/9

12/22/23, 3:45 AM practice
Percentage in Grade 10 57.685
Out[91]:
Salary 204500.000
Name: 0.25, dtype: float64

In [92]: data.quantile(q=[0.25,0.5])

Out[92]: Percentage in Grade 10 Salary

0.25 57.685 204500.0

0.50 64.700 250000.0

In [93]: data.var()

Percentage in Grade 10 9.721836e+01

Out[93]:
Salary 5.885313e+09
dtype: float64

LOGISTIC REGRESSION
In [151… # Import necessary libraries
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report, f1_score

# Create a simple dataset

data = pd.DataFrame({
'Hours_Studied': [2, 3, 4, 5, 6, 7, 8, 9, 10],
'Hours_Slept': [5, 6, 5, 7, 8, 7, 8, 9, 10],
'Pass': [0, 0, 0, 0, 1, 1, 1, 1, 1] # 1 indicates pass, 0 indicates fail
})

# Display the dataset

print("Dataset:")
print(data)

# Split the data into training and testing sets

X = data[['Hours_Studied', 'Hours_Slept']]
y = data['Pass']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_sta

# Create a logistic regression model

model = LogisticRegression()

# Train the model on the training data

model.fit(X_train, y_train)

# Make predictions on the testing data

y_pred = model.predict(X_test)

# Evaluate the model

accuracy = accuracy_score(y_test, y_pred)
print(f"\nAccuracy: {accuracy:.2f}")
print("f1 score: ", f1_score(y_test,y_pred))

localhost:8888/nbconvert/html/practice .ipynb?download=false 3/9

12/22/23, 3:45 AM practice
Dataset:
Hours_Studied Hours_Slept Pass
0 2 5 0
1 3 6 0
2 4 5 0
3 5 7 0
4 6 8 1
5 7 7 1
6 8 8 1
7 9 9 1
8 10 10 1

Accuracy: 1.00
f1 score: 1.0

In [95]: # Display classification report

print("Classification Report:")
print(classification_report(y_test, y_pred))

Classification Report:
precision recall f1-score support

0 1.00 1.00 1.00 1

1 1.00 1.00 1.00 1

accuracy 1.00 2
macro avg 1.00 1.00 1.00 2
weighted avg 1.00 1.00 1.00 2

In [ ]:

In [ ]:

In [ ]:

In [ ]:

MULTINOMIAL REGRESSION
In [115… # Import necessary libraries
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report

# Create a simple dataset

data = pd.DataFrame({
'Hours_Studied': [2, 3, 4, 5, 6, 7, 8, 9, 10],
'Hours_Slept': [5, 6, 5, 7, 8, 7, 8, 9, 10],
'Grade': ['F', 'F', 'F', 'C', 'B', 'C', 'B', 'A', 'A'] # Three classes: F, C,
})

# Display the dataset

print("Dataset:")
print(data)

# Split the data into training and testing sets

localhost:8888/nbconvert/html/practice .ipynb?download=false 4/9

12/22/23, 3:45 AM practice
X = data[['Hours_Studied', 'Hours_Slept']]
y = data['Grade']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_sta

# Create a multinomial logistic regression model

model = LogisticRegression(multi_class='multinomial', solver='lbfgs')

# Train the model on the training data

model.fit(X_train, y_train)

# Make predictions on the testing data

y_pred = model.predict(X_test)

# Evaluate the model

accuracy = accuracy_score(y_test, y_pred)
print(f"\nAccuracy: {accuracy:.2f}")

Dataset:
Hours_Studied Hours_Slept Grade
0 2 5 F
1 3 6 F
2 4 5 F
3 5 7 C
4 6 8 B
5 7 7 C
6 8 8 B
7 9 9 A
8 10 10 A

Accuracy: 1.00

In [119… # Display classification report

print("Classification Report:")
print(classification_report(y_test, y_pred))

Classification Report:
precision recall f1-score support

A 1.00 1.00 1.00 1

F 1.00 1.00 1.00 1

accuracy 1.00 2
macro avg 1.00 1.00 1.00 2
weighted avg 1.00 1.00 1.00 2

Multiple Linear Regression(using sklearn)

In [113… # Import necessary libraries
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

# Create a simple dataset

data = pd.DataFrame({
'Hours_Studied': [2, 3, 4, 5, 6, 7, 8, 9, 10],
'Hours_Slept': [5, 6, 5, 7, 8, 7, 8, 9, 10],
'Score': [55, 65, 50, 80, 90, 75, 85, 95, 100] # Dependent variable
})

localhost:8888/nbconvert/html/practice .ipynb?download=false 5/9

12/22/23, 3:45 AM practice

# Display the dataset

print("Dataset:")
display(data)

# Split the data into training and testing sets

X = data[['Hours_Studied', 'Hours_Slept']]
y = data['Score']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_sta

# Create a multiple linear regression model

model = LinearRegression()

# Train the model on the training data

model.fit(X_train, y_train)

# Make predictions on the testing data

y_pred = model.predict(X_test)

# Evaluate the model

mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"\nMean Squared Error: {mse:.2f}")

print(f"R-squared: {r2:.2f}")

# Display the coefficients and intercept

print("\nCoefficients:")
print(model.coef_)
print("Intercept:", model.intercept_)

Dataset:
Hours_Studied Hours_Slept Score

0 2 5 55

1 3 6 65

2 4 5 50

3 5 7 80

4 6 8 90

5 7 7 75

6 8 8 85

7 9 9 95

8 10 10 100

Mean Squared Error: 6.60

R-squared: 0.97

Coefficients:
[-2.43842365 13.36206897]
Intercept: -4.384236453201979

MLR Using statsmodel

In [140… import statsmodels.api as sm
dataa = pd.DataFrame({

localhost:8888/nbconvert/html/practice .ipynb?download=false 6/9

12/22/23, 3:45 AM practice
'Hours_Studied': [2, 3, 4, 5, 6, 7, 8, 9, 10],
'Hours_Slept': [5, 6, 5, 7, 8, 7, 8, 9, 10],
'Score': [55, 65, 50, 80, 90, 75, 85, 95, 100] # Dependent variable
})
print(dataa)
m = dataa[['Hours_Studied','Hours_Slept']]
n = dataa['Score']

mlr = sm.OLS(n,m).fit()
print("Params:")
print(mlr.params)
y_pred = mlr.predict(m)
print('Y Pred: ')
print(y_pred)

Hours_Studied Hours_Slept Score

0 2 5 55
1 3 6 65
2 4 5 50
3 5 7 80
4 6 8 90
5 7 7 75
6 8 8 85
7 9 9 95
8 10 10 100
Params:
Hours_Studied -1.428571
Hours_Slept 11.890756
dtype: float64
Y Pred:
0 56.596639
1 67.058824
2 53.739496
3 76.092437
4 86.554622
5 73.235294
6 83.697479
7 94.159664
8 104.621849
dtype: float64

In [142… rsquare = r2_score(y_pred,n)

print(r2)

0.9706465820573179

In [143… mlr.summary2()

C:\Users\Ishant\anaconda3\Lib\site-packages\scipy\stats\_stats_py.py:1736: UserWar
ning: kurtosistest only valid for n>=20 ... continuing anyway, n=9
warnings.warn("kurtosistest only valid for n>=20 ... continuing "

localhost:8888/nbconvert/html/practice .ipynb?download=false 7/9

12/22/23, 3:45 AM practice

Out[143]: Model: OLS Adj. R-squared (uncentered): 0.998

Dependent Variable: Score AIC: 48.5980

Date: 2023-12-21 18:23 BIC: 48.9925

No. Observations: 9 Log-Likelihood: -22.299

Df Model: 2 F-statistic: 2623.

Df Residuals: 7 Prob (F-statistic): 8.64e-11

R-squared (uncentered): 0.999 Scale: 10.684

Coef. Std.Err. t P>|t| [0.025 0.975]

Hours_Studied -1.4286 0.7787 -1.8346 0.1092 -3.2699 0.4127

Hours_Slept 11.8908 0.6872 17.3024 0.0000 10.2657 13.5158

Omnibus: 1.260 Durbin-Watson: 1.268

Prob(Omnibus): 0.533 Jarque-Bera (JB): 0.686

Skew: -0.168 Prob(JB): 0.710

Kurtosis: 1.689 Condition No.: 9

Notes:
[1] R² is computed without centering (uncentered) since the model does not contain a
constant.
[2] Standard Errors assume that the covariance matrix of the errors is correctly specified.

In [ ]:

In [107… #Reshaping the data

X_train.values.reshape(-1,1)

array([[ 7],
Out[107]:
[ 7],
[ 2],
[ 5],
[10],
[10],
[ 4],
[ 5],
[ 6],
[ 8],
[ 5],
[ 7],
[ 8],
[ 8]], dtype=int64)

DataFrame from Dictionary

In [106… dataas = pd.DataFrame(data)
dataas

localhost:8888/nbconvert/html/practice .ipynb?download=false 8/9

12/22/23, 3:45 AM practice

Out[106]: Hours_Studied Hours_Slept Pass

0 2 5 0

1 3 6 0

2 4 5 0

3 5 7 0

4 6 8 1

5 7 7 1

6 8 8 1

7 9 9 1

8 10 10 1

In [165…

Cell In[165], line 1

jupyter nbconvert --to FORMAT notebook.ipynb
^
SyntaxError: invalid syntax

In [ ]:

In [ ]:

In [ ]:

In [ ]:

localhost:8888/nbconvert/html/practice .ipynb?download=false 9/9