使用COLAB提前进行H2o AutoML预测

Question

我正在使用此示例 H2O AutoML example with multivariate time series 并从R的即时广播libray中获取数据以使其可再现。我需要帮助，以使其适合于对所给数据造成的打击领先一步。还有其他方法可以进行一步预测

library(nowcasting)
data(BRGDP)
vintage <- PRTDB(mts = BRGDP$base, delay = BRGDP$delay, vintage = "2015-06-01")
base <- window(vintage, start = c(2005,06), frequency = 12)
x <- Bpanel(base = base, trans = BRGDP$trans)
data <- as.data.frame(x)
dataQ = subset(data, select = -c(20:88))
write.csv(dataQ, file = "dataQ.csv")

数据如下图所示，此示例使其可重现。

apt-get install openjdk-8-jdk -qq > /dev/null
!pip install h2o -qq

import pandas as pd
import h2o
from h2o.automl import H2OAutoML

import matplotlib.pyplot as plt
from scipy import stats


%matplotlib inline

h2o.init(nthreads=-1)

from google.colab import files

uploaded = files.upload()



for fn in uploaded.keys():
  print('User uploaded file "{name}" with length {length} bytes'.format(
      name=fn, length=len(uploaded[fn])))

df = pd.read_csv(io.StringIO(uploaded['GTallcombine.csv'].decode('utf-8')))
df.head()

df.reset_index(drop=True,inplace=True)
df_train = df.loc[:int(df.shape[0]*0.8),:]
df_test = df.loc[int(df.shape[0]*0.8):,:]
df_train.head()
df_train.tail()

hf_train = h2o.H2OFrame(df_train)
hf_test = h2o.H2OFrame(df_test)

如何使其提前预报的问题

df2 = df.copy()
num_lags = 3 # number of lags and window lenghts for mean aggregation
delay = 1 # predict target one step ahead
for column in df2:
    for lag in range(1,num_lags+1):
        df2[column + '_lag' + str(lag)] = df2[column].shift(lag*-1-(delay-1))

            df2[column + '_avg_window_length' + str(lag+1)] = df2[column].shift(-1-(delay-1)).rolling(window=lag+1,center=False).mean().shift(1-(lag+1))

df2.dropna(inplace=True) 

mask = (df2.columns.str.contains('pollution') | df2.columns.str.contains('lag') | df2.columns.str.contains('window'))
df_processed = df2[df2.columns[mask]]

# the columns in the processed dataframe
df_processed.columns


y = 'PIM_BI'
X = hf_train.columns
X.remove(y)
aml = H2OAutoML(max_runtime_secs = 600,
                seed = 42)
aml.train(x = X, 
          y = y,
          training_frame = hf_train,
          leaderboard_frame = hf_test)