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()
Imported csv data:
1.01214,0.3609367,-0.01214
1.992202,0.341559,0.007798
2.995016,0.3510846,0.004984
3.974359,0.3405953,0.025641
4.976273,0.3612314,0.023727
5.954718,0.3618527,0.045282
6.984058,0.3536173,0.015942
7.962502,0.3542386,0.037498
8.967653,0.3348767,0.032347
9.969748,0.3532908,0.030252
Error:
runfile('C:/Users/Aidan/.spyder-py3/temp.py', wdir='C:/Users/Aidan/.spyder-py3') Traceback (most recent call last):
File "", line 1, in runfile('C:/Users/Aidan/.spyder-py3/temp.py', wdir='C:/Users/Aidan/.spyder-py3')
File "C:\Users\Aidan\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 705, in runfile execfile(filename, namespace)
File "C:\Users\Aidan\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile exec(compile(f.read(), filename, 'exec'), namespace)
File "C:/Users/Aidan/.spyder-py3/temp.py", line 15, in filtered_data = raw_data[~np.isnan(raw_data["y"])]
File "C:\Users\Aidan\Anaconda3\lib\site-packages\pandas\core\frame.py", line 2685, in getitem return self._getitem_column(key)
File "C:\Users\Aidan\Anaconda3\lib\site-packages\pandas\core\frame.py", line 2692, in _getitem_column return self._get_item_cache(key)
File "C:\Users\Aidan\Anaconda3\lib\site-packages\pandas\core\generic.py", line 2486, in _get_item_cache values = self._data.get(item)
File "C:\Users\Aidan\Anaconda3\lib\site-packages\pandas\core\internals.py", line 4115, in get loc = self.items.get_loc(item)
File "C:\Users\Aidan\Anaconda3\lib\site-packages\pandas\core\indexes\base.py", line 3065, in get_loc return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas_libs\index.pyx", line 140, in pandas._libs.index.IndexEngine.get_loc
File "pandas_libs\index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc
File "pandas_libs\hashtable_class_helper.pxi", line 1492, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas_libs\hashtable_class_helper.pxi", line 1500, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'y'
So without the 3rd column in the CSV this script executes perfectly. I wanted to include the 3rd column of data for an error bar line. How can I implement the y err bar into my script?
plt.errorbar()?