Task1 赛题理解

二手车价格预测task1

数据读取

import pandas as pd
import numpy as np
from IPython.core.interactiveshell import InteractiveShell

InteractivShell.ast_node_interactivity = 'all'
path = 'E:/exer/Datawhale/SecondHandCarPriceForecast/data/'
## 1) 载入训练集和测试集；
Train_data = pd.read_csv(path+'train.csv', sep=' ')
Test_data = pd.read_csv(path+'testB.csv', sep=' ')
print('Train data shape:',Train_data.shape)
print('TestB data shape:',Test_data.shape)

Train data shape: (150000, 31)
TestA data shape: (50000, 30)

Train_data.head()

分类指标评价计算示例

回归指标评价计算示例

# coding=utf-8
import numpy as np
from sklearn import metrics

# MAPE需要自己实现
def mape(y_true, y_pred):
    return np.mean(np.abs((y_pred - y_true) / y_true))

y_true = np.array([1.0, 5.0, 4.0, 3.0, 2.0, 5.0, -3.0])
y_pred = np.array([1.0, 4.5, 3.8, 3.2, 3.0, 4.8, -2.2])

# MSE
print('MSE:',metrics.mean_squared_error(y_true, y_pred))
# RMSE
print('RMSE:',np.sqrt(metrics.mean_squared_error(y_true, y_pred)))
# MAE
print('MAE:',metrics.mean_absolute_error(y_true, y_pred))
# MAPE
print('MAPE:',mape(y_true, y_pred))

MSE: 0.2871428571428571
RMSE: 0.5358571238146014
MAE: 0.4142857142857143
MAPE: 0.1461904761904762

## R2-score
from sklearn.metrics import r2_score
y_true = [3, -0.5, 2, 7]
y_pred = [2.5, 0.0, 2, 8]
print('R2-score:',r2_score(y_true, y_pred))

R2-score: 0.9486081370449679