數據準備for xgboost

xgboost只接受數值

1.分類的輸出變量編碼

# multiclass classification
import pandas
import xgboost
from sklearn import model_selection
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
# load data
data = pandas.read_csv('iris.csv', header=None)
dataset = data.values
# split data into X and y
X = dataset[:,0:4]
Y = dataset[:,4]
# encode string class values as integers
label_encoder = LabelEncoder()
label_encoder = label_encoder.fit(Y)
label_encoded_y = label_encoder.transform(Y)
seed = 7
test_size = 0.33
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, label_encoded_y, test_size=test_size, random_state=seed)
# fit model no training data
model = xgboost.XGBClassifier()
model.fit(X_train, y_train)
print(model)
# make predictions for test data
y_pred = model.predict(X_test)
predictions = [round(value) for value in y_pred]
# evaluate predictions
accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))

關鍵：

label_encoder = LabelEncoder()
label_encoder = label_encoder.fit(Y)
label_encoded_y = label_encoder.transform(Y)
2.將分類的input變量轉化onehot

# binary classification, breast cancer dataset, label and one hot encoded
import numpy
from pandas import read_csv
from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
# load data
data = read_csv('datasets-uci-breast-cancer.csv', header=None)
dataset = data.values
# split data into X and y
X = dataset[:,0:9]
X = X.astype(str)
Y = dataset[:,9]
# encode string input values as integers
encoded_x = None
for i in range(0, X.shape[1]):
	label_encoder = LabelEncoder()
	feature = label_encoder.fit_transform(X[:,i])
	feature = feature.reshape(X.shape[0], 1)
	onehot_encoder = OneHotEncoder(sparse=False)
	feature = onehot_encoder.fit_transform(feature)
	if encoded_x is None:
		encoded_x = feature
	else:
		encoded_x = numpy.concatenate((encoded_x, feature), axis=1)
print("X shape: : ", encoded_x.shape)
# encode string class values as integers
label_encoder = LabelEncoder()
label_encoder = label_encoder.fit(Y)
label_encoded_y = label_encoder.transform(Y)
# split data into train and test sets
seed = 7
test_size = 0.33
X_train, X_test, y_train, y_test = train_test_split(encoded_x, label_encoded_y, test_size=test_size, random_state=seed)
# fit model no training data
model = XGBClassifier()
model.fit(X_train, y_train)
print(model)
# make predictions for test data
y_pred = model.predict(X_test)
predictions = [round(value) for value in y_pred]
# evaluate predictions
accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))

關鍵：

for i in range(0, X.shape[1]):
    label_encoder = LabelEncoder()
    feature = label_encoder.fit_transform(X[:,i])
    feature = feature.reshape(X.shape[0], 1)
    onehot_encoder = OneHotEncoder(sparse=False)
    feature = onehot_encoder.fit_transform(feature)
    if encoded_x is None:
        encoded_x = feature
    else:
        encoded_x = numpy.concatenate((encoded_x, feature), axis=1)
注意這裏只是label_encoder還不行，還要變成onehot形式（因爲不變可能會認爲0比1小即有次序大小的問題）

3.缺失值問題

可以直接啥都不管，因爲xgboost自動處理

# binary classification, missing data
from pandas import read_csv
from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
# load data
dataframe = read_csv("horse-colic.csv", delim_whitespace=True, header=None)
dataset = dataframe.values
# split data into X and y
X = dataset[:,0:27]
Y = dataset[:,27]
# set missing values to 0
X[X == '?'] = 0
# convert to numeric
X = X.astype('float32')
# encode Y class values as integers
label_encoder = LabelEncoder()
label_encoder = label_encoder.fit(Y)
label_encoded_y = label_encoder.transform(Y)
# split data into train and test sets
seed = 7
test_size = 0.33
X_train, X_test, y_train, y_test = train_test_split(X, label_encoded_y, test_size=test_size, random_state=seed)
# fit model no training data
model = XGBClassifier()
model.fit(X_train, y_train)
print(model)
# make predictions for test data
y_pred = model.predict(X_test)
predictions = [round(value) for value in y_pred]
# evaluate predictions
accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))

但是我們也可以手動填充

# binary classification, missing data, impute with mean
import numpy
from pandas import read_csv
from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import Imputer
# load data
dataframe = read_csv("horse-colic.csv", delim_whitespace=True, header=None)
dataset = dataframe.values
# split data into X and y
X = dataset[:,0:27]
Y = dataset[:,27]
# set missing values to 0
X[X == '?'] = numpy.nan
# convert to numeric
X = X.astype('float32')
# impute missing values as the mean
imputer = Imputer()
imputed_x = imputer.fit_transform(X)
# encode Y class values as integers
label_encoder = LabelEncoder()
label_encoder = label_encoder.fit(Y)
label_encoded_y = label_encoder.transform(Y)
# split data into train and test sets
seed = 7
test_size = 0.33
X_train, X_test, y_train, y_test = train_test_split(imputed_x, label_encoded_y, test_size=test_size, random_state=seed)
# fit model no training data
model = XGBClassifier()
model.fit(X_train, y_train)
print(model)
# make predictions for test data
y_pred = model.predict(X_test)
predictions = [round(value) for value in y_pred]
# evaluate predictions
accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))

就是這裏啦：imputer = Imputer()
imputed_x = imputer.fit_transform(X)

當然也可以其他median啊之類的

https://machinelearningmastery.com/data-preparation-gradient-boosting-xgboost-python/