Answers for "why use one hot encoding"

python convert categorical data to one-hot encoding

# Basic syntax:
df_onehot = pd.get_dummies(df, columns=['col_name'], prefix=['one_hot'])
# Where:
#	- get_dummies creates a one-hot encoding for each unique categorical
#		value in the column named col_name
#	- The prefix is added at the beginning of each categorical value 
#		to create new column names for the one-hot columns

# Example usage:
# Build example dataframe:
df = pd.DataFrame(['sunny', 'rainy', 'cloudy'], columns=['weather'])
print(df)
  weather
0   sunny
1   rainy
2  cloudy

# Convert categorical weather variable to one-hot encoding:
df_onehot = pd.get_dummies(df, columns=['weather'], prefix=['one_hot'])
print(df_onehot)
	one_hot_cloudy	 one_hot_rainy   one_hot_sunny
0                0               0               1
1                0               1               0
2                1               0               0

one hot encoding

from sklearn.preprocessing import OneHotEncoder
encoder = preprocessing.OneHotEncoder(handle_unknown='ignore')
y = np.array([1, 2, 1, 3])
y = y.reshape(-1,1)
encoder.fit(y)
y_oh = encoder.transform(y).toarray()
print(y_oh)
>>[[1. 0. 0.]
 [0. 1. 0.]
 [1. 0. 0.]
 [0. 0. 1.]]