CODEWITHSUNDEEP
pythonmachine-learningstatsmodelssklearn-pandas
Anjali
Anjali

Reputation: 187

statsmodels raises TypeError: ufunc 'isfinite' not supported for the input types

I am applying backward elimination using statsmodels.api and the code gives this error `TypeError: ufunc 'isfinite' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ''safe''

I have no clue how to solve it

here is the code

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import  train_test_split
from sklearn.preprocessing import  LabelEncoder, OneHotEncoder
from sklearn.compose import  ColumnTransformer
import statsmodels.api as smf

data = pd.read_csv('F:/Py Projects/ML_Dataset/50_Startups.csv')
dataSlice = data.head(10)

#get data column
readX = data.iloc[:,:4].values
readY = data.iloc[:,4].values

#encoding c3
transformer = ColumnTransformer(
    transformers=[("OneHot",OneHotEncoder(),[3])],
    remainder='passthrough' )
readX = transformer.fit_transform(readX.tolist())
readX = readX[:,1:]

trainX, testX, trainY, testY = train_test_split(readX,readY,test_size=0.2,random_state=0)

lreg = LinearRegression()
lreg.fit(trainX, trainY)
predY = lreg.predict(testX)

readX = np.append(arr=np.ones((50,1),dtype=np.int),values=readX,axis=1)

optimisedX = readX[:,[0,1,2,3,4,5]]
ols = smf.OLS(endog=readX, exog=optimisedX).fit()
print(ols.summary())

here is the error message

Traceback (most recent call last):
  File "F:/Py Projects/ml/BackwardElimination.py", line 33, in <module>
    ols = smf.OLS(endog=readX, exog=optimisedX).fit()
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\regression\linear_model.py", line 838, in __init__
    hasconst=hasconst, **kwargs)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\regression\linear_model.py", line 684, in __init__
    weights=weights, hasconst=hasconst, **kwargs)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\regression\linear_model.py", line 196, in __init__
    super(RegressionModel, self).__init__(endog, exog, **kwargs)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\base\model.py", line 216, in __init__
    super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\base\model.py", line 68, in __init__
    **kwargs)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\base\model.py", line 91, in _handle_data
    data = handle_data(endog, exog, missing, hasconst, **kwargs)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\base\data.py", line 635, in handle_data
    **kwargs)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\base\data.py", line 80, in __init__
    self._handle_constant(hasconst)
  File "C:\Users\udit\AppData\Local\Programs\Python\Python37\lib\site-packages\statsmodels\base\data.py", line 125, in _handle_constant
    if not np.isfinite(ptp_).all():
TypeError: ufunc 'isfinite' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ''safe''

Upvotes: 4

Views: 16794

Answers (3)

Uttam Kumar
Uttam Kumar

Reputation: 11

Today I received the same error.
The root cause is converting numpy dtype object to float64 and assigning to it a new variable and using this variable in a function.

X[1:3]
#array([[1, 0.0, 0.0, 162597.7, 151377.59, 443898.53],
#        [1, 1.0, 0.0, 153441.51, 101145.55, 407934.54]], dtype=object)
X.dtype
#dtype('O')

X1= X.astype(np.float64)
X1[1:2]
#array([[1.0000000e+00, 0.0000000e+00, 0.0000000e+00, 1.625977e+05, 1.5137759e+05, 4.4389853e+05]])
X1.dtype
#dtype('float64')

Upvotes: 1

kiranr
kiranr

Reputation: 2465

just add this line,

X_opt = X[:, [0, 1, 2, 3, 4, 5]] 
X_opt = np.array(X_opt, dtype=float) # <-- this line

convert it to the array and change the datatype.

Upvotes: 5

Rakesh Ghorai
Rakesh Ghorai

Reputation: 51

U need to change the datatype of the readX to int or float64 using numpy. astype( ) function before optimisedX is initialize. Also change endog to readY

readX.astype('float64')
optimisedX = readX[:,[0,1,2,3,4,5]]
ols = smf.OLS(endog=readY, exog=optimisedX).fit()
print(ols.summary())

Upvotes: 5

Related Questions