train test split for images python code example

Example 1: code for test and train split

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
 X, y, test_size=0.33, random_state=42)

Example 2: sklearn split train test

import numpy as np
from sklearn.model_selection import train_test_split

X, y = np.arange(10).reshape((5, 2)), range(5)

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.33, random_state=42)

X_train
# array([[4, 5],
#        [0, 1],
#        [6, 7]])

y_train
# [2, 0, 3]

X_test
# array([[2, 3],
#        [8, 9]])

y_test
# [1, 4]

Example 3: how to split train and test data in r

library(caTools)
sample <- sample.split(data$y, SplitRatio = 0.7)
train_data <- subset(data, sample == TRUE)
test_data <- subset(data, sample == FALSE)

Example 4: svd movielens data train and test

from surprise import Dataset, Reader, SVD, accuracy
from surprise.model_selection import train_test_split
 
# instantiate a reader and read in our rating data
reader = Reader(rating_scale=(1, 5))
data = Dataset.load_from_df(ratings_f[['userId','movieId','rating']], reader)
 
# train SVD on 75% of known rates
trainset, testset = train_test_split(data, test_size=.25)
algorithm = SVD()
algorithm.fit(trainset)
predictions = algorithm.test(testset)
 
# check the accuracy using Root Mean Square Error
accuracy.rmse(predictions)
RMSE: 0.7724
 
# check the preferences of a particular user
user_id = 7010
predicted_ratings = pred_user_rating(user_id)
pdf = pd.DataFrame(predicted_ratings, columns = ['movies','ratings'])
pdf.sort_values('ratings', ascending=False, inplace=True)  
pdf.set_index('movies', inplace=True)
pdf.head(10)