Scribd
Upload
6 views4 pages

Linear Regression Analysis in Python

Experiment 5 code

Uploaded by

maasalamix
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
6 views4 pages

Linear Regression Analysis in Python

Experiment 5 code

Uploaded by

maasalamix
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

Code:

import numpy as np
import [Link] as plt

# Data points
X = [Link]([70, 80, 90, 100, 110, 120, 130, 140, 150, 160])
Y = [Link]([7, 7, 8, 9, 12, 12, 15, 14, 13, 17])

# Number of data points


n = len(X)

# Calculate the sums needed for the slope (w1) and intercept (w0)
sum_X = [Link](X)
sum_Y = [Link](Y)
sum_XY = [Link](X * Y)
sum_X2 = [Link](X**2)

# Calculate w1 (slope) and w0 (intercept)


w1 = (n * sum_XY - sum_X * sum_Y) / (n * sum_X2 - sum_X**2)
w0 = (sum_Y - w1 * sum_X) / n

print(f"Slope (w1): {w1}")


print(f"Intercept (w0): {w0}")

# Predict Y for a given X (e.g., X = 210)


X_new = 210
Y_pred = w0 + w1 * X_new

print(f"Predicted Y for X = {X_new}: {Y_pred}")


# Plotting the graph
[Link](X, Y, color='blue', label='Data points') # Scatter plot for the data points
[Link](X, w0 + w1 * X, color='red', label='Regression line') # Regression line

# Adding labels and title


[Link]('X values')
[Link]('Y values')
[Link]('Linear Regression Line')
[Link]()

# Show the plot


[Link]()

# import numpy as np
# import [Link] as plt

# # Data points
# X = [Link]([70, 80, 90, 100, 110, 120, 130, 140, 150, 160])
# Y = [Link]([7, 7, 8, 9, 12, 12, 15, 14, 13, 17])

# # Number of data points


# n = len(X)

# # Calculate the sums needed for the slope (w1) and intercept (w0)
# sum_X = [Link](X)
# sum_Y = [Link](Y)
# sum_XY = [Link](X * Y)
# sum_X2 = [Link](X**2)

# # Calculate w1 (slope) and w0 (intercept)


# w1 = (n * sum_XY - sum_X * sum_Y) / (n * sum_X2 - sum_X**2)
# w0 = (sum_Y - w1 * sum_X) / n

# print(f"Slope (w1): {w1}")


# print(f"Intercept (w0): {w0}")

# # Predict Y for a given X (e.g., X = 210)


# X_new = 210
# Y_pred = w0 + w1 * X_new

# print(f"Predicted Y for X = {X_new}: {Y_pred}")

# # Plotting
# # Create a range of X values for plotting the regression line
# X_line = [Link](min(X), max(X_new, max(X)), 100)
# Y_line = w0 + w1 * X_line

# # Plot the data points


# [Link](X, Y, color='blue', label='Data Points')

# # Plot the regression line


# [Link](X_line, Y_line, color='red', label='Regression Line')

# # Plot the prediction for X_new


# [Link](X_new, Y_pred, color='green', marker='x', s=100, label=f'Prediction at X
= {X_new}')
# # Labels and title
# [Link]('X')
# [Link]('Y')
# [Link]('Linear Regression')

# # Show legend
# [Link]()

# # Display the plot


# [Link]()
Output:
Slope (w1): 0.10909090909090909
Intercept (w0): -1.1454545454545453
Predicted Y for X = 210: 21.763636363636362

Common questions

Powered by AI

Plotting a regression line in a scatter plot is significant as it visually represents the best-fit line through the data points, allowing one to observe the relationship between the variables. The line simplifies the understanding of trends, pattern detection, and prediction of future values. It helps in assessing the goodness of fit visually by observing the distance of points from the line .

The number of data points (n) impacts the accuracy of linear regression calculations by influencing the reliability of estimates for slope and intercept. More data points typically reduce variability caused by random errors and outliers, improving the stability and accuracy of the model parameters. In calculations, 'n' is integral in both slope and intercept formulas, impacting the denominator that adjusts correlations and averages in the values .

sum_X and sum_Y are used in calculating both the slope and the intercept of the linear regression model. They summarize the total of X and Y values, respectively. In the formula for the slope, they are used to adjust the numerator and denominator for the correlation with XY. In the intercept formula, sum_X and sum_Y adjust the averaged data point alignment vertically along the Y-axis .

The slope (w1) influences how steep the line rises or falls over data points and directly affects the change in Y for a one-unit change in X. The intercept (w0) sets the baseline starting value of Y when X is zero. Together, they define the linear equation's behavior and positioning. The predicted Y is dependent on both, as changes in either parameter affect the linear equation, consequently altering the predicted outcome .

The distribution of data points affects the predicted outcome as it determines the line of best fit. In cases where data points are closely aligned, the linear model is likely to give more accurate predictions. Conversely, a scattered distribution can result in a higher variance and poorer model precision. Skewed or clustered data can bias the slope and intercept, leading to inaccurate predictions .

Prediction for a new data point in linear regression is made using the equation: Y_pred = w0 + w1 * X_new. Here, 'w0' represents the intercept, 'w1' is the slope of the regression line, and 'X_new' is the new X value for which we want to predict the Y value. The output gives the predicted Y coordinate on the regression line for the specified X .

A single linear regression model may oversimplify relationships by assuming linearity, which isn't suited for complex data with nonlinear patterns. It is sensitive to outliers, which can skew predictions and model parameters. The model is unidimensional, failing to capture multifactorial impacts unless extended (e.g., multiple regression). Overfitting can occur with small datasets, while underfitting is possible with complex patterns in large sets .

The slope (w1) in a simple linear regression is calculated using the formula: w1 = (n * sum_XY - sum_X * sum_Y) / (n * sum_X2 - sum_X**2), where 'n' is the number of data points, 'sum_XY' is the summation of the product of X and Y, 'sum_X' is the summation of X values, 'sum_Y' is the summation of Y values, and 'sum_X2' is the summation of the square of X values .

To predict a Y value for a new X using linear regression, first calculate the slope (w1) and intercept (w0) using their respective formulas. Once these parameters are determined, apply the prediction formula Y_pred = w0 + w1 * X_new where X_new is the specified input value. This involves substituting the calculated slope and intercept into the prediction equation .

The intercept (w0) is the value where the regression line crosses the Y-axis, representing the expected Y value when X is zero. It is derived using the formula w0 = (sum_Y - w1 * sum_X) / n, where 'sum_Y' is the sum of all Y values, 'sum_X' is the sum of all X values, 'w1' is the slope, and 'n' is the number of data points .

You might also like