категориальные данные Panda в numerica
sex = train_dataset['Sex'].replace(['female','male'],[0,1])
print(sex)
Black Buzzard
sex = train_dataset['Sex'].replace(['female','male'],[0,1])
print(sex)from sklearn.preprocessing import LabelEncoder
lb_make = LabelEncoder()
obj_df["make_code"] = lb_make.fit_transform(obj_df["make"])
obj_df[["make", "make_code"]].head(11)
from sklearn import preprocessing
lab_encoder = preprocessing.LabelEncoder()
df['column'] = lab_encoder.fit_transform(df['column'])#this will label as one hot vectors (origin is split into 3 columns - USA, Europe, Japan and any one place will be 1 while the others are 0)
dataset['Origin'] = dataset['Origin'].map({1: 'USA', 2: 'Europe', 3: 'Japan'})