mirror of
https://github.com/TheAlgorithms/Python.git
synced 2024-11-27 15:01:08 +00:00
7f04e5cd34
* spelling corrections * review * improved documentation, removed redundant variables, added testing * added type hint * camel case to snake case * spelling fix * review * python --> Python # it is a brand name, not a snake * explicit cast to int * spaces in int list * "!= None" to "is not None" * Update comb_sort.py * various spelling corrections in documentation & several variables naming conventions fix * + char in file name * import dependency - bug fix Co-authored-by: John Law <johnlaw.po@gmail.com>
107 lines
3.5 KiB
Python
107 lines
3.5 KiB
Python
"""
|
|
Linear regression is the most basic type of regression commonly used for
|
|
predictive analysis. The idea is pretty simple: we have a dataset and we have
|
|
features associated with it. Features should be chosen very cautiously
|
|
as they determine how much our model will be able to make future predictions.
|
|
We try to set the weight of these features, over many iterations, so that they best
|
|
fit our dataset. In this particular code, I had used a CSGO dataset (ADR vs
|
|
Rating). We try to best fit a line through dataset and estimate the parameters.
|
|
"""
|
|
import requests
|
|
import numpy as np
|
|
|
|
|
|
def collect_dataset():
|
|
""" Collect dataset of CSGO
|
|
The dataset contains ADR vs Rating of a Player
|
|
:return : dataset obtained from the link, as matrix
|
|
"""
|
|
response = requests.get(
|
|
"https://raw.githubusercontent.com/yashLadha/"
|
|
+ "The_Math_of_Intelligence/master/Week1/ADRvs"
|
|
+ "Rating.csv"
|
|
)
|
|
lines = response.text.splitlines()
|
|
data = []
|
|
for item in lines:
|
|
item = item.split(",")
|
|
data.append(item)
|
|
data.pop(0) # This is for removing the labels from the list
|
|
dataset = np.matrix(data)
|
|
return dataset
|
|
|
|
|
|
def run_steep_gradient_descent(data_x, data_y, len_data, alpha, theta):
|
|
""" Run steep gradient descent and updates the Feature vector accordingly_
|
|
:param data_x : contains the dataset
|
|
:param data_y : contains the output associated with each data-entry
|
|
:param len_data : length of the data_
|
|
:param alpha : Learning rate of the model
|
|
:param theta : Feature vector (weight's for our model)
|
|
;param return : Updated Feature's, using
|
|
curr_features - alpha_ * gradient(w.r.t. feature)
|
|
"""
|
|
n = len_data
|
|
|
|
prod = np.dot(theta, data_x.transpose())
|
|
prod -= data_y.transpose()
|
|
sum_grad = np.dot(prod, data_x)
|
|
theta = theta - (alpha / n) * sum_grad
|
|
return theta
|
|
|
|
|
|
def sum_of_square_error(data_x, data_y, len_data, theta):
|
|
""" Return sum of square error for error calculation
|
|
:param data_x : contains our dataset
|
|
:param data_y : contains the output (result vector)
|
|
:param len_data : len of the dataset
|
|
:param theta : contains the feature vector
|
|
:return : sum of square error computed from given feature's
|
|
"""
|
|
prod = np.dot(theta, data_x.transpose())
|
|
prod -= data_y.transpose()
|
|
sum_elem = np.sum(np.square(prod))
|
|
error = sum_elem / (2 * len_data)
|
|
return error
|
|
|
|
|
|
def run_linear_regression(data_x, data_y):
|
|
""" Implement Linear regression over the dataset
|
|
:param data_x : contains our dataset
|
|
:param data_y : contains the output (result vector)
|
|
:return : feature for line of best fit (Feature vector)
|
|
"""
|
|
iterations = 100000
|
|
alpha = 0.0001550
|
|
|
|
no_features = data_x.shape[1]
|
|
len_data = data_x.shape[0] - 1
|
|
|
|
theta = np.zeros((1, no_features))
|
|
|
|
for i in range(0, iterations):
|
|
theta = run_steep_gradient_descent(data_x, data_y, len_data, alpha, theta)
|
|
error = sum_of_square_error(data_x, data_y, len_data, theta)
|
|
print("At Iteration %d - Error is %.5f " % (i + 1, error))
|
|
|
|
return theta
|
|
|
|
|
|
def main():
|
|
""" Driver function """
|
|
data = collect_dataset()
|
|
|
|
len_data = data.shape[0]
|
|
data_x = np.c_[np.ones(len_data), data[:, :-1]].astype(float)
|
|
data_y = data[:, -1].astype(float)
|
|
|
|
theta = run_linear_regression(data_x, data_y)
|
|
len_result = theta.shape[1]
|
|
print("Resultant Feature vector : ")
|
|
for i in range(0, len_result):
|
|
print("%.5f" % (theta[0, i]))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|