ValueError: Input contains infinity or a value too large for dtype('float32'). code example

Example 1: ValueError: Input contains NaN, infinity or a value too large for dtype('float32').

# Loads your dataset, drops labels and response variable as usual...
df = pd.read_csv('train_test.csv', sep=',')
X = df.drop(["label_1","label_2","response_var"], axis=1)
y = df['response_var']

# this will print TRUE or FALSE for positions containing or not NaN
# values in your dataset

print(np.isnan(X))

Example 2: Input contains NaN, infinity or a value too large for dtype('float64').

import numpy as np

# generate example matrix
matrix = np.random.rand(5,5)
matrix[0,:] = np.inf
matrix[2,:] = -np.inf
>>> matrix
array([[       inf,        inf,        inf,        inf,        inf],
       [0.87362809, 0.28321499, 0.7427659 , 0.37570528, 0.35783064],
       [      -inf,       -inf,       -inf,       -inf,       -inf],
       [0.72877665, 0.06580068, 0.95222639, 0.00833664, 0.68779902],
       [0.90272002, 0.37357483, 0.92952479, 0.072105  , 0.20837798]])

# find min and max values for each column, ignoring nan, -inf, and inf
mins = [np.nanmin(matrix[:, i][matrix[:, i] != -np.inf]) for i in range(matrix.shape[1])]
maxs = [np.nanmax(matrix[:, i][matrix[:, i] != np.inf]) for i in range(matrix.shape[1])]

# go through matrix one column at a time and replace  + and -infinity 
# with the max or min for that column
for i in range(matrix.shape[1]):
    matrix[:, i][matrix[:, i] == -np.inf] = mins[i]
    matrix[:, i][matrix[:, i] == np.inf] = maxs[i]

>>> matrix
array([[0.90272002, 0.37357483, 0.95222639, 0.37570528, 0.68779902],
       [0.87362809, 0.28321499, 0.7427659 , 0.37570528, 0.35783064],
       [0.72877665, 0.06580068, 0.7427659 , 0.00833664, 0.20837798],
       [0.72877665, 0.06580068, 0.95222639, 0.00833664, 0.68779902],
       [0.90272002, 0.37357483, 0.92952479, 0.072105  , 0.20837798]])