时间序列分析

显示缺少一个文件 h5

有些地方是%，%%，会出错，显示无效，没搞懂是哪里有问题？

整个代码基本为：

工具包导入&数据读取

‘’’
安装工具

!pip install netCDF4 #这里不懂是什么？

‘’’
import pandas as pd
import numpy as np
import tensorflow as tf
from tensorflow.keras.optimizers import Adam
import matplotlib.pyplot as plt
import scipy
from netCDF4 import Dataset
import netCDF4 as nc
import gc

%matplotlib inline

1.数据读取

1.1 SODA_label处理

#将标签转化为我们熟悉的pandas形式

label_path = ‘./data/SODA_label.nc’
label_trans_path = ‘./data/’
nc_label = Dataset(label_path,‘r’)

years = np.array(nc_label[‘year’][:])
months = np.array(nc_label[‘month’][:])

year_month_index = []
vs = []
for i,year in enumerate(years):
for j,month in enumerate(months):
year_month_index.append(‘year_{}month{}’.format(year,month))
vs.append(np.array(nc_label[‘nino’][i,j]))

df_SODA_label = pd.DataFrame({‘year_month’:year_month_index})
df_SODA_label[‘year_month’] = year_month_index
df_SODA_label[‘label’] = vs

df_SODA_label.to_csv(label_trans_path + ‘df_SODA_label.csv’,index = None)

df_SODA_label.head()

SODA_train处理

SODA_path = ‘./data/SODA_train.nc’
nc_SODA = Dataset(SODA_path,‘r’)

def trans_df(df, vals, lats, lons, years, months):
‘’’
(100, 36, 24, 72) – year, month,lat,lon
‘’’
for j,lat_ in enumerate(lats):
for i,lon_ in enumerate(lons):
c = 'lat_lon_{}{}’.format(int(lat),int(lon_))
v = []
for y in range(len(years)):
for m in range(len(months)):
v.append(vals[y,m,j,i])
df[c] = v
return df

year_month_index = []

years = np.array(nc_SODA[‘year’][:])
months = np.array(nc_SODA[‘month’][:])
lats = np.array(nc_SODA[‘lat’][:])
lons = np.array(nc_SODA[‘lon’][:])

for year in years:
for month in months:
year_month_index.append(‘year_{}month{}’.format(year,month))

df_sst = pd.DataFrame({‘year_month’:year_month_index})
df_t300 = pd.DataFrame({‘year_month’:year_month_index})
df_ua = pd.DataFrame({‘year_month’:year_month_index})
df_va = pd.DataFrame({‘year_month’:year_month_index})

%%time
df_sst = trans_df(df = df_sst, vals = np.array(nc_SODA[‘sst’][:]), lats = lats, lons = lons, years = years, months = months)
df_t300 = trans_df(df = df_t300, vals = np.arra