写在前面
一、为什么要引入类别变量：对现有的数据进行预处理，再训练模型，使得训练出来的模型效果更好
二、什么是类别变量：类别变量又名分类变量，顾名思义，类别变量就是能表示类别的名词，比如说，男，女；汽车制造业，手工业，农业等。
本文基于kaggle教程介绍三个方法
1、丢弃分类变量
找到数据中的分类变量，drop掉
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
from sklearn.preprocessing import OrdinalEncoder,OneHotEncoder
pd.set_option('display.max_columns',None)
# Function for comparing different approaches
def score_dataset(X_train, X_valid, y_train, y_valid):
model = RandomForestRegressor(n_estimators=100, random_state=0)
model.fit(X_train, y_train)
preds = model.predict(X_valid)
return mean_absolute_error(y_valid, preds)
# Read the data
data = pd.read_csv('../machineLearning/temp/archive/melb_data.csv')
# Separate target from predictors
y = data.Price
X = data.drop(['Price'], axis=1)
# Divide data into training and validation subsets
X_train_full, X_valid_full, y_train, y_valid = train_test_split(X, y, train_size=0.8, test_size=0.2,
random_state=0)
# 删除存在空值的列
cols_with_missing = [col for col in X_train_full.columns if X_train_full[col].isnull().any()]
X_train_full.drop(cols_with_missing, axis=1, inplace=True)
X_valid_full.drop(cols_with_missing, axis=1, inplace=True)
# "Cardinality" means the number of unique values in a column
# Select categorical columns with relatively low cardinality (convenient but arbitrary)
low_cardinality_cols = [cname for cname in X_train_full.columns if X_train_full[cname].nunique() < 10 and
X_train_full[cname].dtype == "object"]
# 选择num列
numerical_cols = [cname for cname in X_train_full.columns if X_train_full[cname].dtype in ['int64', 'float64']]
# Keep selected columns only
my_cols = low_cardinality_cols + numerical_cols
X_train = X_train_full[my_cols].copy()
X_valid = X_valid_full[my_cols].copy()
#找到object列
s = (X_train.dtypes == 'object')
object_cols = list(s[s].index)
print("Categorical variables:")
print(object_cols)
#直接将类别变量去掉
drop_X_train = X_train.select_dtypes(exclude=['object'])
drop_X_valid = X_valid.select_dtypes(exclude=['object'])
print("MAE from Approach 1 (Drop categorical variables):")
print(score_dataset(drop_X_train, drop_X_valid, y_train, y_valid))
2、Ordinal Encoding
对数据中分类变量的值进行从0到排号
# Make copy to avoid changing original data
label_X_train = X_train.copy()
label_X_valid = X_valid.copy()
# Apply ordinal encoder to each column with categorical data
ordinal_encoder = OrdinalEncoder()
#print(label_X_train[object_cols])
label_X_train[object_cols] = ordinal_encoder.fit_transform(X_train[object_cols])
label_X_valid[object_cols] = ordinal_encoder.transform(X_valid[object_cols])
#print(label_X_train[object_cols])
print("MAE from Approach 2 (Ordinal Encoding):")
print(score_dataset(label_X_train, label_X_valid, y_train, y_valid))
3、One-Hot Encoding
OH_encoder = OneHotEncoder(handle_unknown='ignore', sparse=False)
OH_cols_train = pd.DataFrame(OH_encoder.fit_transform(X_train[object_cols]))
OH_cols_valid = pd.DataFrame(OH_encoder.transform(X_valid[object_cols]))
#print(OH_cols_train.head())
# One-hot encoding removed index; put it back
OH_cols_train.index = X_train.index
OH_cols_valid.index = X_valid.index
print(OH_cols_train.shape)
# Remove categorical columns (will replace with one-hot encoding)
num_X_train = X_train.drop(object_cols, axis=1)
num_X_valid = X_valid.drop(object_cols, axis=1)
print(num_X_train.shape)
# Add one-hot encoded columns to numerical features
OH_X_train = pd.concat([num_X_train, OH_cols_train], axis=1)
OH_X_valid = pd.concat([num_X_valid, OH_cols_valid], axis=1)
print(OH_X_train.shape)
print("MAE from Approach 3 (One-Hot Encoding):")
print(score_dataset(OH_X_train, OH_X_valid, y_train, y_valid))
