task4 建模调参

优化内存：
来源 https://www.kaggle.com/gemartin/load-data-reduce-memory-usage

可以节省60%以上的内存。

import pandas as pd
import numpy as np
 
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() / 1024**2
    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() / 1024**2
    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
def import_data(file,encoding):
    """create a dataframe and optimize its memory usage"""
    df = pd.read_csv(file, parse_dates=True, keep_date_col=True,encoding=encoding)
    df = reduce_mem_usage(df)
    return df

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
1线性回归模型：
线性回归对于特征的要求；
处理长尾分布；log
理解线性回归模型；

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']
from sklearn.linear_model import LinearRegression
model = LinearRegression(normalize=True)
model = model.fit(train_X, train_y)

可视化

from matplotlib import pyplot as plt
subsample_index = np.random.randint(low=0, high=len(train_y), size=50)
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()

对于长尾分布的标签进行log以更符合正态分布。
效果图：

2模型性能验证：
在使用训练集对参数进行训练的时候，经常会发现人们通常会将一整个训练集分为三个部分（比如mnist手写训练集）。一般分为：训练集（train_set），评估集（valid_set），测试集（test_set）这三个部分。这其实是为了保证训练效果而特意设置的。其中测试集很好理解，其实就是完全不参与训练的数据，仅仅用来观测测试效果的数据。而训练集和评估集则牵涉到下面的知识了。

因为在实际的训练中，训练的结果对于训练集的拟合程度通常还是挺好的（初始条件敏感），但是对于训练集之外的数据的拟合程度通常就不那么令人满意了。因此我们通常并不会把所有的数据集都拿来训练，而是分出一部分来（这一部分不参加训练）对训练集生成的参数进行测试，相对客观的判断这些参数对训练集之外的数据的符合程度。这种思想就称为交叉验证（Cross Validation）
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；
3模型对比：

常用线性模型；

result = pd.DataFrame(result)
result.index = ['cv' + str(x) for x in range(1, 6)]
result
model = LinearRegression().fit(train_X, train_y_ln)
print('intercept:'+ str(model.intercept_))
sns.barplot(abs(model.coef_), continuous_feature_names)
model = Ridge().fit(train_X, train_y_ln)
print('intercept:'+ str(model.intercept_))
sns.barplot(abs(model.coef_), continuous_feature_names)
#
model = Lasso().fit(train_X, train_y_ln)
print('intercept:'+ str(model.intercept_))
sns.barplot(abs(model.coef_), continuous_feature_names)

常用非线性模型；

from sklearn.linear_model import LinearRegression
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.neural_network import MLPRegressor
from xgboost.sklearn import XGBRegressor
from lightgbm.sklearn import LGBMRegressor
models = [LinearRegression(),
          DecisionTreeRegressor(),
          RandomForestRegressor(),
          GradientBoostingRegressor(),
          MLPRegressor(solver='lbfgs', max_iter=100), 
          XGBRegressor(n_estimators = 100, objective='reg:squarederror'), 
          LGBMRegressor(n_estimators = 100)]
          result = dict()
for model in models:
    model_name = str(model).split('(')[0]
    scores = cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error))
    result[model_name] = scores
    print(model_name + ' is finished')
    result = pd.DataFrame(result)
result.index = ['cv' + str(x) for x in range(1, 6)]
result