2024 iFLYTEK A.I.开发者大赛-讯飞开放平台

TabNet： 模型也是我在这个比赛一个意外收获，这个模型在比赛之中可用。但是需要GPU资源，否则运行真的是太慢了。后面针对这个模型我会写出如何使用的方法策略。

        比赛结束后有与其他两位选手聊天，他们都是对数据做了很多分析，有的甚至直接使用Lasso就work了，效果还挺不错的。特征工程无敌呀。        

        真个代码部分，了解下有关特征工程的部分就行了，模型部分可以慢慢消化。当作一个新的知识点学习吧。

直接上代码

import matplotlib.pyplot as plt
import numpy as np
import pandas as pdfrom tqdm import tqdm
from sklearn.model_selection import KFoldfrom pytorch_tabnet.metrics import Metric
from pytorch_tabnet.tab_model import TabNetRegressor
import torch
from torch.optim import Adam, SGD
from torch.optim.lr_scheduler import ReduceLROnPlateau, CosineAnnealingWarmRestarts
from sklearn.metrics import mean_absolute_error
import tracebackimport warningswarnings.filterwarnings("ignore")plt.rcParams['font.sans-serif'] = ['PingFang HK']  # 用来正常显示中文标签
plt.rcParams["axes.unicode_minus"] = False  # 该语句解决图像中的“-”负号的乱码问题
pd.set_option('precision', 10)
pd.set_option('display.max_rows', None)# 时间解析模块
def parse_date(train_df=None):train_df['datetime'] = pd.to_datetime(train_df['时间'])train_df['timestamp'] = train_df['datetime'].astype('int64') / 10000000train_df['year'] = train_df['datetime'].dt.yeartrain_df['month'] = train_df['datetime'].dt.monthtrain_df['day'] = train_df['datetime'].dt.daytrain_df['hour'] = train_df['datetime'].dt.hourtrain_df["minute"] = train_df['datetime'].dt.minutetrain_df['dayofweek'] = train_df['datetime'].dt.dayofweek# train_df['datetime'].dt.dayofmonthreturn train_dfdef same_position_tempture_resid(train_df, index=[]):for i in index:train_df[f'下部温度{i}_resid'] = train_df[f'下部温度{i}'] - train_df[f'下部温度设定{i}']train_df[f'下部温度{i}_dist_4'] = train_df[f'下部温度设定4'] - train_df[f'下部温度设定{i}']train_df[f'下部温度{i}_dist_4_moth_100'] = (train_df[f'下部温度{i}_dist_4'] >= 99) * 1return train_dfdf_train = pd.read_csv("../data/train.csv")
df_test = pd.read_csv("../data/test.csv")
submit = pd.read_csv("../data/submit.csv")
df_train = parse_date(df_train)
df_test = parse_date(df_test)df_train = df_train.sort_values("datetime")
df_train = df_train.reset_index(drop=True)
df_train['train'] = 1df_train.loc[1057, '下部温度9'] = 829df_test = df_test.sort_values("datetime")
df_test = df_test.reset_index(drop=True)
df_test['train'] = 0flow_cols = [col for col in df_train.columns if "流量" in col]
up_temp_sets = [col for col in df_train.columns if "上部温度设定" in col]
down_temp_sets = [col for col in df_train.columns if "下部温度设定" in col]
up_tempture = [col for col in df_train.columns if "上部温度" in col and col not in up_temp_sets]
down_tempture = [col for col in df_train.columns if "下部温度" in col and col not in down_temp_sets]# train_df.columns.tolist()
import resmall_cols = ['下部温度5', '上部温度8', '上部温度9','上部温度10','上部温度11','上部温度12','上部温度13','上部温度14','上部温度15','上部温度16','上部温度17','下部温度3','下部温度4','下部温度6','下部温度7','下部温度8','下部温度9','下部温度10','下部温度11','下部温度12','下部温度13','下部温度14','下部温度15','下部温度16','下部温度17'] + ['上部温度1','上部温度2','上部温度3','上部温度4','上部温度5','上部温度6','上部温度7','下部温度1','下部温度2',]def get_same_temp(test_df, cols):for col in cols:nums = re.findall("\d+", col)num = nums[0]if "上部温度" in col:print(num, col)test_df[col] = test_df[f'上部温度设定{num}']elif "下部温度" in col:test_df[col] = test_df[f'下部温度设定{num}']return test_dfdf_test = get_same_temp(df_test, small_cols)
df = pd.concat([df_train, df_test])
df = df.sort_values(['year', 'month', 'day', 'hour', "minute"])
df = df.reset_index(drop=True)down_label = ['下部温度1', '下部温度2', '下部温度3']
up_label = ['上部温度7', '上部温度1', '上部温度2', '上部温度3', '上部温度4', '上部温度5', '上部温度6']
cat_cols = ['year', 'month', 'day', 'hour', 'minute', 'dayofweek']keep_cols = df_test.columns.tolist()def resid_model(y, y_pred):# residual plotsy_pred = pd.Series(y_pred, index=y.index)resid = y - y_predmean_resid = resid.mean()std_resid = resid.std()z = abs(resid) / (y + 0.01)# print(z)n_outliers = sum(abs(resid) > 10000)outliers = y[(abs(resid) > 10000)].indexprint(outliers)plt.figure(figsize=(15, 5))ax_131 = plt.subplot(1, 3, 1)plt.plot(y, y_pred, '.')plt.xlabel('y')plt.ylabel('y_pred');plt.title('corr = {:.3f}'.format(np.corrcoef(y, y_pred)[0][1]))ax_132 = plt.subplot(1, 3, 2)plt.plot(y, y - y_pred, '.')plt.xlabel('y')plt.ylabel('y - y_pred');plt.title('std resid = {:.3f}'.format(std_resid))ax_133 = plt.subplot(1, 3, 3)z.plot.hist(bins=50, ax=ax_133)plt.xlabel('z')plt.title('{:.0f} samples with z>3'.format(n_outliers))plt.show()# return outliersdef get_down_tempture_sets_resid(df, diffed_col="下部温度设定4",diff_col='下部温度设定1'):distacnce = 0if "上部" in diff_col:print(f"----- {diff_col}_diff_{diffed_col}")df['上部温度设定4_diff_上部温度设定1'] = df['上部温度设定4'] - df['上部温度设定1']df[f'{diffed_col}_diff_{diff_col}'] = df[diffed_col] - df[diff_col]df['上部温度设定4_div_上部温度设定1'] = df['上部温度设定4'] / df['上部温度设定1']df[f'{diffed_col}_div_{diff_col}'] = df[diffed_col] / df[diff_col]df['flag'] = (df['上部温度设定4_diff_上部温度设定1'] > 300) * 1else:df['下部温度设定4_diff_下部温度设定1'] = df['下部温度设定4'] - df['下部温度设定1']df['下部温度设定4_div_下部温度设定1'] = df['下部温度设定4'] / df['下部温度设定1']df[f'{diffed_col}_diff_{diff_col}'] = df[diffed_col] - df[diff_col]df[f'{diffed_col}_div_{diff_col}'] = df[diffed_col] / df[diff_col]distacnce = 300df['flag'] = (df['下部温度设定4_diff_下部温度设定1'] > 300) * 1return dfdef get_same_type_tempure(row, df_train, label, woindows):try:heads = woindowstrain_flag = int(row['train'])hour = row['hour']minute = row['minute']timesamp = row['timestamp']flag = row['flag']nums = re.findall("\d+", label)num = int(nums[0])chars = re.findall("(\w+)(\d+)", label)[0][0]label_map_set_col = f"{chars}设定{num}"set_temps = row[label_map_set_col]# (df_train[label_map_set_col]==set_temps)&df_temp_ = df_train[(df_train[label_map_set_col] == set_temps) & (df_train['flag'] == flag) & (df_train['hour'] == hour) & (df_train['timestamp'] < timesamp)]df_temp = df_temp_.tail(woindows)# df_temp_2 = df_temp_.head(30)if len(df_temp) == 0:return set_temps, set_temps, 0, set_temps, set_temps, set_tempsmin_ = df_temp[label].min()max_ = df_temp[label].max()std_ = df_temp[label].std()mean_ = df_temp[label].mean()median_ = df_temp[label].median()ewm_ = df_temp[label].ewm(span=heads, adjust=False).mean().values[-1]del df_tempreturn min_, max_, std_, mean_, median_, ewm_except Exception as e:print(traceback.format_exc())def predict_result(df, train_df=None, result_df=None, label="下部温度1"):result_cols = result_df.columns.tolist()nums = re.findall("\d+", label)num = nums[0]chars = re.findall("(\w+)(\d+)", label)[0][0]df[f'{label}_new_label'] = (df[label] - df[f"{chars}设定{num}"])label_new = f'{label}_new_label'label_map_set_col = f"{chars}设定{num}"df[f'{label_map_set_col}_ratio'] = df[label_map_set_col].pct_change()# df[f'{label_map_set_col}_ratio']if chars in "下部温度":balance_col = "下部温度设定4"new_cols = [f'{balance_col}_diff_{label_map_set_col}', f'{balance_col}_div_{label_map_set_col}','下部温度设定4_diff_下部温度设定1', '下部温度设定4_div_下部温度设定1']else:balance_col = "上部温度设定4"new_cols = list(set(['上部温度设定4_diff_上部温度设定1', '上部温度设定4_div_上部温度设定1',f'{balance_col}_diff_{label_map_set_col}', f'{balance_col}_div_{label_map_set_col}']))down_df = get_down_tempture_sets_resid(df, balance_col, diff_col=label_map_set_col)train_df = down_df[down_df['train'] == 1].reset_index(drop=True)his_feats = []for wind in [7, 28]:his_feat = [f"{label}_min_{wind}", f"{label}_max_{wind}",f"{label}_std_{wind}", f"{label}_mean_{wind}",f"{label}_median_{wind}", f"{label}_ewm_{wind}"]his_feats.extend(his_feat)down_df[his_feat] = down_df.apply(lambda x: get_same_type_tempure(x, train_df, label, wind), axis=1,result_type="expand")# return down_df# print(down_df[his_feats].isna().sum())down_df = down_df.fillna(-99)for use_flag in [0, 1]:max_epoches = 60if use_flag==1:max_epoches = 100df_train = down_df[(down_df['train'] == 1) & (down_df['flag'] == use_flag)].reset_index(drop=True)# df_train = down_train_dfdf_test = down_df[(down_df['train'] == 0) & (down_df['flag'] == use_flag)].reset_index(drop=True)# print(df_test.unique())print("Nan shape", df_test[his_feats].isna().sum())# print(df_test[df_test[his_feats].isna()].head())print(down_df.shape, df_train.shape, df_test.shape)feats = [f'流量{num}','上部温度设定1','year', 'month', 'day', 'hour','minute', 'dayofweek', ] + new_cols + [f'{label_map_set_col}_ratio'] + his_featsfeats = list(set(feats))cat_cols = ['year', 'month', 'day', 'hour', 'minute', 'dayofweek']cat_idxs = [i for i, f in enumerate(feats) if f in cat_cols]cat_dims = [df_train[i].nunique() for i in cat_cols]# print(df_train[feats].head())# print(cat_idxs)# print(cat_dims)tabnet_params = dict(cat_idxs=[],cat_dims=[],cat_emb_dim=1,n_d=16,n_a=16,n_steps=2,  # 模型获取能力代表gamma=2,n_independent=2,n_shared=2,lambda_sparse=0,optimizer_fn=Adam,optimizer_params=dict(lr=(2e-2)),mask_type="entmax",scheduler_params=dict(T_0=200, T_mult=1, eta_min=1e-4, last_epoch=-1, verbose=False),# 学习速率自动调整scheduler_fn=CosineAnnealingWarmRestarts,seed=42,verbose=10,)split = 5# kf = KFold(n_splits=split, shuffle=False, random_state=2021)folds = KFold(n_splits=split, shuffle=True, random_state=1314)  # 1314oof = np.zeros((len(df_train), 1))importance = 0pred_y = np.zeros(len(df_test))val_all = []# for fold, (train_idx, val_idx) in enumerate(train_splits):for fold, (train_idx, val_idx) in enumerate(folds.split(df_train)):print(f'--------------------------- {len(train_idx)}', fold)val_all.extend(val_idx)print(f'Training fold {fold + 1}')X_train, X_val = df_train.loc[train_idx, feats].values, df_train.loc[val_idx, feats].valuesy_train, y_val = df_train.loc[train_idx, label_new].values.reshape(-1, 1), df_train.loc[val_idx, label_new].values.reshape(-1, 1)model = TabNetRegressor(**tabnet_params)model.fit(X_train, y_train,eval_set=[(X_val, y_val)],max_epochs=max_epoches,patience=50,batch_size=64,virtual_batch_size=32,num_workers=8,drop_last=False,eval_metric=[MYMAE],loss_fn=my_mean)oof[val_idx] = model.predict(X_val)# print(model.predict(df_test[feats].values))pred_y += model.predict(df_test[feats].values).flatten() / split#     if save_model:#         joblib.dump(value=model, filename=f'../model/lgb_5fold_{fold}.m')print(f'labe = {label} use_flag = {use_flag} mae = ',mean_absolute_error(oof.reshape(-1) + df_train[label_map_set_col], df_train[label]))# resid_model(df_train[label_new], oof)result_df = result_df[result_cols]df_test[label + "_add"] = pred_yresult_df = result_df.merge(df_test[cat_cols + [label + "_add"] + his_feats], on=cat_cols, how="left")# print(result_df.head())result_df.loc[~result_df[label + "_add"].isna(), label] = result_df.loc[~result_df[label + "_add"].isna(), label + "_add"] + result_df.loc[~result_df[label + "_add"].isna(), label_map_set_col]return result_df.reset_index(drop=True)[result_cols + his_feats]# df['day'].nunique()
class MYMAE(Metric):def __init__(self):self._name = "mymae"self._maximize = Falsedef __call__(self, y_true, y_score):return mean_absolute_error(y_true, y_score)def my_mean(y_pred, y_true):return torch.mean(torch.abs(y_true - y_pred)).clone()# up_label+down_label
for label in tqdm((down_label + up_label)[5:]):print(f"-------------------{label}")df_test = predict_result(df, df_train, df_test[keep_cols], label)df_test['上部温度1'] = df_test['上部温度1'].clip(upper=410)
x = pd.concat([df_train, df_test]).sort_values(['year', 'month', 'day', 'hour', "minute"]).reset_index(drop=True)
submit = pd.read_csv("../data/submit.csv")
submit_cols = submit.columns.tolist()
df_test[submit_cols].to_csv("../data/tabnet_submit_his_winds_label_last_5.csv",index=False, encoding='utf_8_sig')