I want to use LinearRegression and linregress to caculate Intercept,X_Variable_1,R_Square,Significance_F just like regression analysis in Excel.
When I use this code to do it, there is no mistake.
from sklearn.linear_model import LinearRegression
import pandas as pd
import numpy as np
from scipy.stats import linregress
from decimal import *
def calculate_parameters():
list_a=[['2018', '3', 'aa', 'aa', 93,1884.7746222667, 165.36153386251098], ['2018', '3', 'bb', 'bb', 62, 665.6392779848, 125.30386609565328], ['2018', '3', 'cc', 'cc', 89, 580.2259903521, 160.19280253775514]]
df = pd.DataFrame(list_a)
X = df.iloc[:, 5]
y = df.iloc[:, 6]
X1 = X.values.reshape(-1, 1)
y1 = y.values.reshape(-1, 1)
clf = LinearRegression()
clf.fit(X1, y1)
yhat = clf.predict(X1)
para_Intercept = clf.intercept_[0]
para_X_Variable_1 = clf.coef_[0][0]
SS_Residual = sum((y1 - yhat) ** 2)
SS_Total = sum((y1 - np.mean(y1)) ** 2)
para_R_Square = 1 - (float(SS_Residual)) / SS_Total
adjusted_r_squared = 1 - (1 - para_R_Square) * (len(y1) - 1) / (len(y1) - X1.shape[1] - 1)
para_a = linregress(X, y)
para_Significance_F = para_a[3]
print("Intercept:"+str(para_Intercept))
print("X_Variable_1:"+str(para_X_Variable_1))
print("R_Square:" + str(para_R_Square[0]))
print("Significance_F:" + str(para_Significance_F))
if __name__ == "__main__":
calculate_parameters()
The output is:
Intercept:133.10871357512195
X_Variable_1:0.016460552337949654
R_Square:0.3039426453800934
Significance_F:0.6282563718649847
But in fact,list_a likes this:
list_a = [['2018', '3', 'aa', 'aa', 93, Decimal('1884.7746222667'), 165.36153386251098],
['2018', '3', 'bb', 'bb', 62, Decimal('665.6392779848'), 125.30386609565328],
['2018', '3', 'cc', 'cc', 89, Decimal('580.2259903521'), 160.19280253775514]]
The 6th column is decimal type.
When I change list_a,likes this:
from sklearn.linear_model import LinearRegression
import pandas as pd
import numpy as np
from scipy.stats import linregress
from decimal import *
def calculate_parameters():
# list_a=[['2018', '3', 'aa', 'aa', 93,1884.7746222667, 165.36153386251098], ['2018', '3', 'bb', 'bb', 62, 665.6392779848, 125.30386609565328], ['2018', '3', 'cc', 'cc', 89, 580.2259903521, 160.19280253775514]]
list_a=[['2018', '3', 'aa', 'aa', 93,Decimal('1884.7746222667'), 165.36153386251098], ['2018', '3', 'bb', 'bb', 62, Decimal('665.6392779848'), 125.30386609565328], ['2018', '3', 'cc', 'cc', 89, Decimal('580.2259903521'), 160.19280253775514]]
df = pd.DataFrame(list_a)
X = df.iloc[:, 5]
y = df.iloc[:, 6]
X1 = X.values.reshape(-1, 1)
y1 = y.values.reshape(-1, 1)
clf = LinearRegression()
clf.fit(X1, y1)
yhat = clf.predict(X1)
para_Intercept = clf.intercept_[0]
para_X_Variable_1 = clf.coef_[0][0]
SS_Residual = sum((y1 - yhat) ** 2)
SS_Total = sum((y1 - np.mean(y1)) ** 2)
para_R_Square = 1 - (float(SS_Residual)) / SS_Total
adjusted_r_squared = 1 - (1 - para_R_Square) * (len(y1) - 1) / (len(y1) - X1.shape[1] - 1)
para_a = linregress(X, y)
para_Significance_F = para_a[3]
print("Intercept:"+str(para_Intercept))
print("X_Variable_1:"+str(para_X_Variable_1))
print("R_Square:" + str(para_R_Square[0]))
print("Significance_F:" + str(para_Significance_F))
if __name__ == "__main__":
calculate_parameters()
The error is:
Traceback (most recent call last):
File "E:/test_opencv/MyTest.py", line 32, in calculate_parameters()
File "E:/test_opencv/MyTest.py", line 24, in calculate_parameters para_a = linregress(X, y)
File "E:\Anaconda3\lib\site-packages\scipy\stats_stats_mstats_common.py", line 79, in linregress ssxm, ssxym, ssyxm, ssym = np.cov(x, y, bias=1).flat
File "E:\Anaconda3\lib\site-packages\numpy\lib\function_base.py", line 3085, in cov avg, w_sum = average(X, axis=1, weights=w, returned=True)
File "E:\Anaconda3\lib\site-packages\numpy\lib\function_base.py", line 1163, in average if scl.shape != avg.shape:
AttributeError: 'float' object has no attribute 'shape'
How to fix the error?