How to split data using Time Based in Test and Train Respectively

问题

How to split data into Train and Test by using time-based split.

I know that train_test_split splits it randomly how to split it based on Time.

  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42) 
  # this splits the data randomly as 67% test and 33% train

How to Split the same data set based on time as 67% train and 33% test?

The dataset has a column TimeStamp.

I tried searching on the similar questions but was not sure about the approach.

Can someone explain briefly

回答1:

On time-series datasets, data splitting takes place in a different way. See this link for more info. Alternatively, you can try TimeSeriesSplit from scikit-learn package. So the main idea is this, suppose you have 10 points of data according to timestamp. Now the splits will be like this :

Split 1 : 
Train_indices : 1 
Test_indices  : 2


Split 2 : 
Train_indices : 1, 2 
Test_indices  : 3


Split 3 : 
Train_indices : 1, 2, 3 
Test_indices  : 4

Split 4 : 
Train_indices : 1, 2, 3, 4 
Test_indices  : 5

So on and so forth. You can check the example shown in the link above to get a better idea of how TimeSeriesSplit works in sklearn

Update If you have a separate time column, you can simply sort the data based on that column and apply timeSeriesSplit as mentioned above to get the splits.

In order to ensure 67% training and 33% testing data in final split, specify number of splits as following:

no_of_split = int((len(data)-3)/3)

Example

X = np.array([[1, 2], [3, 4], [1, 2], [3, 4],[1, 2], [3, 4],[3, 4],[1, 2],     [3, 4],[3, 4],[1, 2], [3, 4] ])
y = np.array([1, 2, 3, 4, 5, 6,7,8,9,10,11,12])
tscv = TimeSeriesSplit(n_splits=int((len(y)-3)/3))
for train_index, test_index in tscv.split(X):
     print("TRAIN:", train_index, "TEST:", test_index)

     #To get the indices 
     X_train, X_test = X[train_index], X[test_index]
     y_train, y_test = y[train_index], y[test_index]

OUTPUT :

('TRAIN:', array([0, 1, 2]), 'TEST:', array([3, 4, 5]))
('TRAIN:', array([0, 1, 2, 3, 4, 5]), 'TEST:', array([6, 7, 8]))
('TRAIN:', array([0, 1, 2, 3, 4, 5, 6, 7, 8]), 'TEST:', array([ 9, 10, 11]))

回答2:

One easy way to do it..

First: sort the data by time

Second:

import numpy as np 
train_set, test_set= np.split(data, [int(.67 *len(data))])

That makes the train_set with the first 67% of the data, and the test_set with rest 33% of the data.

回答3:

If you have a simple dataset where each row is an observation (e.g. a non-time-series dataset for a classification problem) and you would like to split it into train and test, this function will split into train and test based on a column of dates:

import pandas as pd
import numpy as np
from math import ceil

def train_test_split_sorted(X, y, test_size, dates):
"""Splits X and y into train and test sets, with test set separated by most recent dates.

    Example:
    --------
    >>> from sklearn import datasets

    # Fake dataset:
    >>> gen_data = datasets.make_classification(n_samples=10000, n_features=5)
    >>> dates = np.array(pd.date_range('2016-01-01', periods=10000, freq='5min'))
    >>> np.random.shuffle(dates)
    >>> df = pd.DataFrame(gen_data[0])
    >>> df['date'] = dates
    >>> df['target'] = gen_data[1]

    # Separate:
    >>> X_train, X_test, y_train, y_test = train_test_split_sorted(df.drop('target', axis=1), df['target'], 0.33, df['date'])

    >>> print('Length train set: {}'.format(len(y_train)))
    Length train set: 8000
    >>> print('Length test set: {}'.format(len(y_test)))
    Length test set: 2000
    >>> print('Last date in train set: {}'.format(X_train['date'].max()))
    Last date in train set: 2016-01-28 18:35:00
    >>> print('First date in test set: {}'.format(X_test['date'].min()))
    First date in test set: 2016-01-28 18:40:00
    """

    n_test = ceil(test_size * len(X))

    sorted_index = [x for _, x in sorted(zip(np.array(dates), np.arange(0, len(dates))), key=lambda pair: pair[0])]
    train_idx = sorted_index[:-n_test]
    test_idx = sorted_index[-n_test:]

    if isinstance(X, (pd.Series, pd.DataFrame)):
        X_train = X.iloc[train_idx]
        X_test = X.iloc[test_idx]
    else:
        X_train = X[train_idx]
        X_test = X[test_idx]
    if isinstance(y, (pd.Series, pd.DataFrame)):
        y_train = y.iloc[train_idx]
        y_test = y.iloc[test_idx]
    else:
        y_train = y[train_idx]
        y_test = y[test_idx]

    return X_train, X_test, y_train, y_test

The dates argument could actually be any kind of array or Series which you would like to use to sort your data.

In your case, you should call: X_train, X_test, y_train, y_test = train_test_split_sorted(X, y, 0.333, TimeStamp) with TimeStamp being the array or column where you have the information about the timestamp of each observation.

来源：https://stackoverflow.com/questions/50879915/how-to-split-data-using-time-based-in-test-and-train-respectively

标签

python

scikit-learn

timestamp

train-test-split