def col_feature2(df):
cate_cols = ['制动踏板状态', '驾驶员离开提示','主驾驶座占用状态', '驾驶员安全带状态',
'手刹状态', '整车钥匙状态', '整车当前档位状态']
cate_cols2 = []
# 类别特征编码
for col in cate_cols:
df[col+'cate'] = df[col].astype('category').cat.codes
cate_cols2.append(col+'cate')
df_code_dict = {col:{code:cate for code,cate in enumerate(df[col].astype('category').cat.categories)}
for col in cate_cols}
df['整车钥匙状态catestd'] = df['整车钥匙状态cate'].rolling(window=5,center=True).std()
# 条件筛选数据
df = df [(df['电池包主负继电器状态cate']==0)] # 停车条件1
df = df [(df['if_on']==0) | (df['车速']>20)] # 停车条件2 判断是否启动阶段，或者车速过大的异常清空
df = df [(df['if_off']<-3) | (df['车速']!=0)] # 停车条件3 判断是否停车阶段，或者车速异常大于0的情况
# 车速分桶
bin1 = [-0.1,0.01,0.5,1.5,3,100]
df['v_bin'] = pd.cut(df['车速'], bin1, labels=False)
# 加速踏板特征
df['a0'] = df.apply(lambda x: 1 if (x['加速踏板位置']>0) else 0,axis=1)
df['a_min5'] = df['a_min5'] - df['v_bin']*df['v_bin']/2 - df['a0']*1.5
df['a_mean5'] = df['a_mean5'] - df['v_bin']*df['v_bin']/2 - df['a0']*1.5
# df['a_min5'] = df['a_min5'] - df['v_bin']*df['v_bin'] - df['a0']*3
# df['a_mean5'] = df['a_mean5'] - df['v_bin']*df['v_bin'] - df['a0']*3
df['v_diff1'] = df['v_diff1'] - df['v_bin']*df['v_bin'] - df['a0']*3
df['v_diff3'] = df['v_diff3'] - df['v_bin']*df['v_bin'] - df['a0']*3
# 加速度分桶
bin1 = [-100,-15,-10,-6,-3,-0.01,0.1,100]
df['v_diff3_bin'] = pd.cut(df['v_diff3'], bin1, labels=False)
ori_cols = ['加速踏板位置', '电池包主负继电器状态', '电池包主正继电器状态', '制动踏板状态',
'驾驶员离开提示', '主驾驶座占用状态', '驾驶员安全带状态', '手刹状态', '整车钥匙状态', '低压蓄电池电压',
'整车当前档位状态', '整车当前总电流', '整车当前总电压','车速', '方向盘转角']
cate_cols = ['电池包主负继电器状态cate','制动踏板状态cate', '驾驶员离开提示cate','主驾驶座占用状态cate',
'驾驶员安全带状态cate', '手刹状态cate', '整车钥匙状态cate','整车当前档位状态cate',]
choose_cols = ['time_delta', 'time_delta_5','if_on','a0','v_bin','v_diff3','v_diff2','v_diff4']
df = df.drop(ori_cols+cate_cols+choose_cols,axis=1)
return df,df_code_dict
df_trnall2_LGB , df_code_dict1= col_feature2(df_trnall_LGB)
print('trn',df_trnall2_LGB.shape)
df_testall2_LGB, df_code_dict2 = col_feature2(df_testall_LGB)
print('test',df_testall2_LGB.shape)
print(df_trnall2_LGB.columns)
# df_testall2_LGB.to_csv('./test_data.csv',encoding='GBK',index=False)
# df_code_dict1 == df_code_dict2
# df_code_dict1
