Question

This is an open-ended lab. Using Python, run a linear regression analysis on data you have collected from public domain.

   

Recommended packages:

• scikit-learn

• numpy

• matplotlib

• pandas   

Deliverables:

1. python code [.py file(s)]

2. Explanation of work

Create an original how-to document with step by step instructions you have followed to create your program. Your document should be used as an adequate tutorial for someone to reproduce your work by following the steps/instructions.

Answer 1

STEP 1. IMPORT ALL THE LIBRARIES REQUIRED FOR THE ANALYSIS

STEP 2. IMPORT THE DATA FOR THE ANALYSIS FROM A URL AND SHOW SOME ENTRIES

STEP 3. VISUALIZING THE DATA USING A REGPLOT

STEP 4. SPLITTING THE DATASET INTO TWO PARTS: TRAINING PART AND TESTING PART

TRAINING PART HELPS IN TRAINING THE LINER REGRESSION MODEL.

TESTING PART HELPS IN MEASURING THE PERFORMANCE OF OUR TRAINED MODEL

STEP 5. IMPORTING THE LINEAR REGRESSION MODEL FROM THE SCiKIT-LEARN LIBRARY AND FITTING THE MODEL TO TRAINING DATASET.

STEP 6. VISUALIZING THE REGRESSION LINE OVER THE DATASET

STEP 7. CALCULATING THE SCORE FOR THE TRAINED MODEL USING TESTING DATASET

CODE:

STEP 1.

%matplotlib inline

# Imports

import matplotlib.pyplot as plt

import matplotlib as mpl

import pandas as pd

import seaborn as sns

import sklearn

import numpy as np

STEP 2.

url = "https://raw.githubusercontent.com/ludobouan/linear-regression-sklearn/master/challenge_dataset.txt"

df = pd.read_csv(url, names=['X','Y'])

df.head()

STEP 3.

sns.regplot(x='X', y='Y', data=df, fit_reg=False)

plt.show()

STEP 4.

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = np.asarray(train_test_split(df['X'], df['Y'], test_size=0.1))

STEP 5.

from sklearn.linear_model import LinearRegression

reg = LinearRegression()

reg.fit(X_train.values.reshape(-1,1), y_train.values.reshape(-1,1))

STEP 6.

x_line = np.arange(5,25).reshape(-1,1)

sns.regplot(x=df['X'], y=df['Y'], data=df, fit_reg=False)

plt.plot(x_line, reg.predict(x_line))

plt.show()

STEP 7.

print('Score: ', reg.score(X_test.values.reshape(-1,1), y_test.values.reshape(-1,1)))

THANK YOU!

(NOTE SOMETIMES IF YOU TRY TO COPY THE PYTHON CODE IT SHOWS IDENTATION DUE TO ZERO WIDTH SPACE PROBLEM SO IF POSSIBLE WRITE DOWN THE ABOVE CODE)