import pandas as pd
df = pd.read_excel('------.xlsx')
df.head()

df['类别'].value_counts()
技术类    336
教辅类    333
办公类    331
Name: 类别, dtype: int64
df['彩印'].value_counts()
0    648
1    352
Name: 彩印, dtype: int64
df['纸张'].value_counts()
双胶纸    615
铜版纸    196
书写纸    189
Name: 纸张, dtype: int64

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
df['类别'] = le.fit_transform(df['类别'])  # 处理类别
# 将类别一列处理后，我们可以使用value_counts()方法查看转化效果：
df['类别'].value_counts()
1    336
2    333
0    331
Name: 类别, dtype: int64
# 另外一种文本内容转为数值的方法，注意不要再运行完上面的代码后运行，因为上面的内容已经被替代完毕了，如果想尝试，需要重新运行，并且，先运行下面的代码
# df['类别'] = df['类别'].replace({'办公类': 0, '技术类': 1, '教辅类': 2})  
# df['类别'].value_counts()
# 下面我们使用同样的方法处理“纸张”一列：
le = LabelEncoder()
df['纸张'] = le.fit_transform(df['纸张'])
# 此时的表格如下：
df.head()

X = df.drop(columns='价格') 
y = df['价格']

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)

from sklearn.ensemble import GradientBoostingRegressor
model = GradientBoostingRegressor(random_state=123)
model.fit(X_train, y_train)
GradientBoostingRegressor(alpha=0.9, criterion='friedman_mse', init=None,
             learning_rate=0.1, loss='ls', max_depth=3, max_features=None,
             max_leaf_nodes=None, min_impurity_decrease=0.0,
             min_impurity_split=None, min_samples_leaf=1,
             min_samples_split=2, min_weight_fraction_leaf=0.0,
             n_estimators=100, n_iter_no_change=None, presort='auto',
             random_state=123, subsample=1.0, tol=0.0001,
             validation_fraction=0.1, verbose=0, warm_start=False)

from yellowbrick.regressor import PredictionError
visualizer = PredictionError(model)
visualizer.fit(X_train, y_train)
print('得分：',visualizer.score(X_test,y_test))
visualizer.poof()
得分： 0.8741691363311168

import matplotlib
matplotlib.rcParams['font.sans-serif']=['SimHei']
matplotlib.rcParams['axes.unicode_minus']=False  # 用来正常显示负号
from yellowbrick.features.importances import FeatureImportances
viz = FeatureImportances(model)
viz.fit(X, y)
viz.poof()

# # 分类模型，通过如下代码可以查看官方介绍
# from sklearn.ensemble import AdaBoostClassifier
# AdaBoostClassifier?
# # 回归模型，通过如下代码可以查看官方介绍
# from sklearn.ensemble import AdaBoostRegressor
# AdaBoostRegressor?