Found input variables with inconsistent numbers of samples: [2935848, 2935849]

feature_names = ["date","shop_id", "item_id", "item_price", "item_cnt_day"]
feature_names

X_train = train[feature_names]
print(X_train.shape)
X_train.head()

X_sales = sales[feature_names]
print(X_sales.shape)
X_sales.head()

from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

X_train, X_sales, y_train, y_sales = train_test_split(X_train, X_sales, test_size=0.3)


feature_names = ["date","shop_id", "item_id", "item_price", "item_cnt_day"]
feature_names
​
X_train = train[feature_names]
print(X_train.shape)
X_train.head()
​
X_sales = sales[feature_names]
print(X_sales.shape)
X_sales.head()
​
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
​
X_train, X_sales, y_train, y_sales = train_test_split(X_train, X_sales, test_size=0.3)
​

​ (2935848, 5) (2935849, 5)

ValueError Traceback (most recent call last) in 13 from sklearn.metrics import mean_squared_error 14 ---> 15 X_train, X_sales, y_train, y_sales = train_test_split(X_train, X_sales, test_size=0.3) 16

~/anaconda3/envs/aiffel/lib/python3.7/site-packages/sklearn/model_selection/_split.py in train_test_split(*arrays, **options) 2125 raise TypeError("Invalid parameters passed: %s" % str(options)) 2126 -> 2127 arrays = indexable(*arrays) 2128 2129 n_samples = _num_samples(arrays[0])

~/anaconda3/envs/aiffel/lib/python3.7/site-packages/sklearn/utils/validation.py in indexable(*iterables) 291 """ 292 result = [_make_indexable(X) for X in iterables] --> 293 check_consistent_length(*result) 294 return result 295

~/anaconda3/envs/aiffel/lib/python3.7/site-packages/sklearn/utils/validation.py in check_consistent_length(*arrays) 255 if len(uniques) > 1: 256 raise ValueError("Found input variables with inconsistent numbers of" --> 257 " samples: %r" % [int(l) for l in lengths]) 258 259

ValueError: Found input variables with inconsistent numbers of samples: [2935848, 2935849]