Python_Basics | Shell commands , Files , Text Processing

import os
from PIL import Image as PImage
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
from scipy.stats import chisquare


# Read in csv file
# File: https://github.com/mGalarnyk/Python_Tutorials/blob/master/Python_Basics/Linear_Regression/linear.csv
raw_data = pd.read_csv(r"C:\Users\Aidan\Desktop\NEW TASK\Amos_2001_4p2_APD_CONC_Fig2C_OC.csv")

# Removes rows with NaN in them
filtered_data = raw_data[~np.isnan(raw_data["y"])] 


x_y = np.array(filtered_data)

x, y, y_err = x_y[:,0], x_y[:,1], x_y[:,2]


# Reshaping
x, y = x.reshape(-1,1), y.reshape(-1, 1)

# Linear Regression Object 
lin_regression = LinearRegression()

# Fitting linear model to the data
lin_regression.fit(x,y)

# Get slope of fitted line
m = lin_regression.coef_

# Get y-Intercept of the Line
b = lin_regression.intercept_

# Get Predictions for original x values
# you can also get predictions for new data
predictions = lin_regression.predict(x)
chi= chisquare(predictions, y)

# following slope intercept form 
print ("formula: y = {0}x + {1}".format(m, b)) 
print(chi)

# Plot the Original Model (Black) and Predictions (Blue)
plt.scatter(x, y,  color='black')
plt.plot(x, predictions, color='blue',linewidth=3)
plt.errorbar(x, y, yerr=y_err, fmt='o', capsize=4, color='black')
plt.show()