matplotlib

分类变量

import matplotlib.pyplot as plt
data = {'apple': 10, 'orange': 15, 'lemon': 5, 'lime': 20}
names = list(data.keys())
values = list(data.values())
#直方图，散点图和折线图
fig, axs = plt.subplots(1, 3, figsize=(9, 3), sharey=True)
axs[0].bar(names, values)
axs[1].scatter(names, values)
axs[2].plot(names, values)
fig.suptitle('Categorical Plotting')

#双线
cat = ["bored", "happy", "bored", "bored", "happy", "bored"]
dog = ["happy", "happy", "happy", "happy", "bored", "bored"]
activity = ["combing", "drinking", "feeding", "napping", "playing", "washing"]

fig, ax = plt.subplots()
ax.plot(activity, dog, label="dog")
ax.plot(activity, cat, label="cat")
ax.legend()

plt.show()

image.png
image.png

饼图

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
df1 = pd.Series(3 * np.random.rand(4),index = ('a','b','c','d'),name = 'pie')
df1.plot.pie(figsize = (6,6))
plt.show()

image.png

箱型图

df3 = pd.DataFrame(np.random.rand(10,4),columns=('a','b','c','d'))
df3.plot.box()
plt.show()

image.png

lgb

import lightgbm as lgb
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

print('数据...')
x_train = np.random.random((1000,10))
y_train = np.random.rand(1000)>0.5
x_test = np.random.random((100,10))
y_test = np.random.randn(100)>0.5

# 导入到lightgbm矩阵
lgb_train = lgb.Dataset(x_train, y_train)
lgb_test = lgb.Dataset(x_test, y_test, reference=lgb_train)

# 设置参数
params = {
    'num_leaves': 5,
    'metric': ('auc', 'loss'),#可以设置多个评价指标
    'verbose': 0
}
# if (evals_result and gbm) not in locbals():
    # global evals_result,gbm 
#如果是局部变量的话，推荐把他们变成全局变量，这样plot的代码位置不受限制
evals_result = {}  #记录训练结果所用

print('开始训练...')
# train
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=100,
                valid_sets=[lgb_train, lgb_test],
                evals_result=evals_result,#非常重要的参数,一定要明确设置
                verbose_eval=10)

print('画出训练结果...')
ax = lgb.plot_metric(evals_result, metric='auc')
#metric的值与之前的params里面的值对应
plt.show()

image.png

print('画特征重要性排序...')
ax = lgb.plot_importance(gbm, max_num_features=10)#max_features表示最多展示出前10个重要性特征，可以自行设置
plt.show()

image.png