时间序列天气预测

import pandas as pd import numpy as np import xgboost as xgb from xgboost.sklearn import XGBClassifier from sklearn import model_selection, metrics from sklearn.model_selection import train_test_split from sklearn.metrics import f1_score, roc_auc_score, accuracy_score import warnings warnings.filterwarnings(module='sklearn*', action='ignore', category=DeprecationWarning) from sklearn import datasets from collections import Counter import os import pandas as pd import pandas as pd import numpy as np import xgboost as xgb import matplotlib.pylab as plt # %matplotlib inline from sklearn.model_selection import GridSearchCV from sklearn.model_selection import train_test_split plt.rcParams['font.sans-serif'] = ['SimHei'] plt.rcParams['axes.unicode_minus'] = False data = pd.read_csv("数字化处理历史真实数据.csv") # 1 3 7 是 预测列 data = data.fillna(0) # ['日期', '星期', '最高气温', '最低气温', '天气', '风向', '级数'] data_x=data[['最高气温', '最低气温', '天气', '风向', '级数']].values data_x=np.array(data_x,dtype=np.float16) print(data_x) # 序列长度 int_sequence_len=3 # 每个序列的长度 int_a = 5 train_x = [] train_y = [] for i in range(0, len(data_x)-int_sequence_len,1): train_x.append(data_x[i:i+int_sequence_len]) train_y.append(data_x[i+int_sequence_len][1]) print(len(train_x), len(train_y)) # 划分验证集和测试集 x_train, x_test, y_train, y_test = train_test_split(np.array(train_x), np.array(train_y), test_size=0.2, random_state=1) x_train = x_train.reshape(len(x_train),-1) # 三维度数据 全部数据长度 序列长度 每个序列维度 y_train = y_train.reshape(len(y_train),1) print(x_train.shape,y_train.shape) x_test = x_test.reshape(len(x_test),-1) # y_test = y_test.reshape(-1,1) from sklearn.model_selection import GridSearchCV #Need to research #research_one: n_epoch #research_one: max_depth #定义xgboost模型 xgb1 = xgb.XGBRegressor() # learning_rate =0.12, # n_estimators=150, # max_depth=5, # min_child_weight=1, # gamma=0, # subsample=0.8, # colsample_bytree=0.8, # objective= 'reg:squarederror', # reg_alpha= 0, # reg_lambda= 1, # nthread=4, # scale_pos_weight=1, # seed=27 param_test1 = { 'min_child_weight': [1, 2, 3,4,5,6,8], 'max_depth':[1,2, 3, 4, 5, 6, 7,8], 'learning_rate':[0.09,0.1,0.12,0.13,0.14], 'n_estimators':[100,120,150] } sklearn_model_raw = GridSearchCV(estimator = xgb1, param_grid = param_test1, n_jobs=4, cv=5) sklearn_model_raw.fit(x_train, y_train) pred_test_raw = sklearn_model_raw.predict(x_test) from sklearn.metrics import mean_squared_error # 均方误差 from sklearn.metrics import mean_absolute_error # 平方绝对误差 from sklearn.metrics import r2_score # R square test_mse = mean_squared_error(y_test, pred_test_raw) print('mse Score: %.6f mse' % (test_mse)) test_mae = mean_absolute_error(y_test, pred_test_raw) print('mae Score: %.6f mae' % (test_mae)) test_R2 = r2_score(y_test, pred_test_raw) print('R2 Score: %.6f R2' % (test_R2)) # 所有画图 len_ = [i for i in range(len(y_test))] plt.xlabel('标签', fontsize=8) plt.ylabel('均值', fontsize=8) plt.plot(len_, y_test, label='y_test', color="blue") plt.plot(len_, pred_test_raw, label='y1_pred_lstm', color="yellow") plt.legend(['truh', 'predict']) plt.title("最低气温预测走势图") plt.show() plt.clf() x_test=[22,18,4,3,1,27,17,0,5,2,28,19,1,7,2] x_test=np.array(x_test).reshape(1,15) pred_test_raw = sklearn_model_raw.predict(x_test) print("预测：", pred_test_raw)