代码拉取完成,页面将自动刷新
"""
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 numpy as np
import requests
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/ADRvsRating.csv",
timeout=10,
)
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(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(f"At Iteration {i + 1} - Error is {error:.5f}")
return theta
def mean_absolute_error(predicted_y, original_y):
"""Return sum of square error for error calculation
:param predicted_y : contains the output of prediction (result vector)
:param original_y : contains values of expected outcome
:return : mean absolute error computed from given feature's
"""
total = sum(abs(y - predicted_y[i]) for i, y in enumerate(original_y))
return total / len(original_y)
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(len_result):
print(f"{theta[0, i]:.5f}")
if __name__ == "__main__":
main()
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。