3/6/24, 9:59 AM Untitled27.
ipynb - Colaboratory
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
%matplotlib inline
Data = pd.read_csv('Salary_Data - Salary_Data.csv')
# Display basic info about the dataset
Data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 30 entries, 0 to 29
Data columns (total 2 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 YearsExperience 30 non-null float64
1 Salary 30 non-null int64
dtypes: float64(1), int64(1)
memory usage: 608.0 bytes
# Display descriptive statistics of the dataset
Data.describe()
YearsExperience Salary
count 30.000000 30.000000
mean 5.313333 76003.000000
std 2.837888 27414.429785
min 1.100000 37731.000000
25% 3.200000 56720.750000
50% 4.700000 65237.000000
75% 7.700000 100544.750000
max 10.500000 122391.000000
# Plot pairwise relationships in the dataset
sns.pairplot(Data)
https://colab.research.google.com/drive/1kvXbQLsxeB40qzEbiBRoPPq-tqCGiUU3#scrollTo=Haca6ahBBeB3&printMode=true 1/5
3/6/24, 9:59 AM Untitled27.ipynb - Colaboratory
<seaborn.axisgrid.PairGrid at 0x78cced27a410>
# Plot heatmap of correlations
sns.heatmap(Data.corr(), annot=True)
https://colab.research.google.com/drive/1kvXbQLsxeB40qzEbiBRoPPq-tqCGiUU3#scrollTo=Haca6ahBBeB3&printMode=true 2/5
3/6/24, 9:59 AM Untitled27.ipynb - Colaboratory
<Axes: >
# Plot distribution of Salary
sns.distplot(Data["Salary"])
https://colab.research.google.com/drive/1kvXbQLsxeB40qzEbiBRoPPq-tqCGiUU3#scrollTo=Haca6ahBBeB3&printMode=true 3/5
3/6/24, 9:59 AM Untitled27.ipynb - Colaboratory
<ipython-input-7-f50739657602>:2: UserWarning:
`distplot` is a deprecated function and will be removed in seaborn v0.14.0.
Please adapt your code to use either `displot` (a figure-level function with
similar flexibility) or `histplot` (an axes-level function for histograms).
For a guide to updating your code to use the new functions, please see
https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751
sns.distplot(Data["Salary"])
<Axes: xlabel='Salary', ylabel='Density'>
# Assuming you have a threshold to classify whether salary is above a certain level
threshold = 70000 # Example threshold
# Creating a binary target variable based on the threshold
Data['AboveThreshold'] = (Data['Salary'] > threshold).astype(int)
# Splitting the dataset into train and test sets
X = Data[['YearsExperience']]
y = Data['AboveThreshold']
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=21
# Training the logistic regression model
from sklearn.linear_model import LogisticRegression
log_reg = LogisticRegression()
log_reg.fit(X_train, y_train)
https://colab.research.google.com/drive/1kvXbQLsxeB40qzEbiBRoPPq-tqCGiUU3#scrollTo=Haca6ahBBeB3&printMode=true 4/5
3/6/24, 9:59 AM Untitled27.ipynb - Colaboratory
▾ LogisticRegression
LogisticRegression()
# Making predictions
predictions = log_reg.predict(X_test)
# Evaluating the model
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
accuracy = accuracy_score(y_test, predictions)
conf matrix = confusion matrix(y test predictions)
https://colab.research.google.com/drive/1kvXbQLsxeB40qzEbiBRoPPq-tqCGiUU3#scrollTo=Haca6ahBBeB3&printMode=true 5/5
