学习目标

线性回归模型：
- 线性回归对于特征的要求；
- 处理长尾分布；
- 理解线性回归模型；
模型性能验证：
- 评价函数与目标函数；
- 交叉验证方法；
- 留一验证方法；
- 针对时间序列问题的验证；
- 绘制学习率曲线；
- 绘制验证曲线；
嵌入式特征选择：
- Lasso回归；
- Ridge回归；
- 决策树；
模型对比：
- 常用线性模型；
- 常用非线性模型；
模型调参：
- 贪心调参方法；
- 网格调参方法；
- 贝叶斯调参方法；

代码示例

读取数据

import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings('ignore')

# reduce_mem_usage 函数通过调整数据类型，帮助我们减少数据在内存中占用的空间
def reduce_mem_usage(df):
    """ iterate through all the columns of a dataframe and modify the data type
        to reduce memory usage.        
    """
    start_mem = df.memory_usage().sum() 
    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
    
    for col in df.columns:
        col_type = df[col].dtype
        
        if col_type != object:
            c_min = df[col].min()
            c_max = df[col].max()
            if str(col_type)[:3] == 'int':
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
                    df[col] = df[col].astype(np.int16)
                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
                    df[col] = df[col].astype(np.int32)
                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)  
            else:
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
        else:
            df[col] = df[col].astype('category')

    end_mem = df.memory_usage().sum() 
    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    return df

1	sample_feature = reduce_mem_usage(pd.read_csv('data_for_tree.csv'))

1	continuous_feature_names = [x for x in sample_feature.columns if x not in ['price','brand','model','brand']]

线性回归 & 五折交叉验证 & 模拟真实业务情况

sample_feature = sample_feature.dropna().replace('-', 0).reset_index(drop=True)
sample_feature['notRepairedDamage'] = sample_feature['notRepairedDamage'].astype(np.float32)
train = sample_feature[continuous_feature_names + ['price']]

train_X = train[continuous_feature_names]
train_y = train['price']

简单建模

from sklearn.linear_model import LinearRegression

model = LinearRegression(normalize=True)
model = model.fit(train_X, train_y)

# 查看训练的线性回归模型的截距（intercept）与权重(coef)
'intercept:'+ str(model.intercept_)

sorted(dict(zip(continuous_feature_names, model.coef_)).items(), key=lambda x:x[1], reverse=True)

1
2
3

from matplotlib import pyplot as plt

subsample_index = np.random.randint(low=0, high=len(train_y), size=50)

# 绘制特征v_9的值与标签的散点图
# 图片发现模型的预测结果（蓝色点）与真实标签（黑色点）的分布差异较大
# 且部分预测值出现了小于0的情况，说明我们的模型存在一些问题
plt.scatter(train_X['v_9'][subsample_index], train_y[subsample_index], color='black')
plt.scatter(train_X['v_9'][subsample_index], model.predict(train_X.loc[subsample_index]), color='blue')
plt.xlabel('v_9')
plt.ylabel('price')
plt.legend(['True Price','Predicted Price'],loc='upper right')
print('The predicted price is obvious different from true price')
plt.show()

# 通过作图我们发现数据的标签（price）呈现长尾分布，不利于我们的建模预测。
# 原因是很多模型都假设数据误差项符合正态分布，而长尾分布的数据违背了这一假设。
import seaborn as sns
print('It is clear to see the price shows a typical exponential distribution')
plt.figure(figsize=(15,5))
plt.subplot(1,2,1)
sns.distplot(train_y)
plt.subplot(1,2,2)
sns.distplot(train_y[train_y < np.quantile(train_y, 0.9)])