ValueError: Found input variables with inconsistent numbers of samples: [2750, 1095] [closed]

Question

What is this error and what do I do to fix it? I cannot change my data.

 X = train[['id', 'listing_type', 'floor', 'latitude', 'longitude', 
             'beds', 'baths','total_rooms','square_feet','group','grades']]
    Y = test['price']
    n = pd.get_dummies(train.group)  

This is how the training data looks like:

id  listing_type    floor   latitude    longitude   beds    baths   total_rooms square_feet grades  high_price_high_freq    high_price_low_freq low_price
265183  10  4   40.756224   -73.962506  1   1   3   790 2   1   0   0   0
270356  10  7   40.778010   -73.962547  5   5   9   4825    2   1   0   0
176718  10  25  40.764955   -73.963483  2   2   4   1645    2   1   0   0
234589  10  5   40.741448   -73.994216  3   3   5   2989    2   1   0   0
270372  10  5   40.837000   -73.947787  1   1   3   1045    2   0   0   1

The error code is:

from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, random_state=0)
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)

error message:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-479-ca78b7b5f096> in <module>()
      1 from sklearn.cross_validation import train_test_split
----> 2 X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, random_state=0)
      3 from sklearn.linear_model import LinearRegression
      4 regressor = LinearRegression()
      5 regressor.fit(X_train, y_train)

~\Anaconda3\lib\site-packages\sklearn\cross_validation.py in train_test_split(*arrays, **options)
   2057     if test_size is None and train_size is None:
   2058         test_size = 0.25
-> 2059     arrays = indexable(*arrays)
   2060     if stratify is not None:
   2061         cv = StratifiedShuffleSplit(stratify, test_size=test_size,

~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in indexable(*iterables)
    227         else:
    228             result.append(np.array(X))
--> 229     check_consistent_length(*result)
    230     return result
    231 

~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_consistent_length(*arrays)
    202     if len(uniques) > 1:
    203         raise ValueError("Found input variables with inconsistent numbers of"
--> 204                          " samples: %r" % [int(l) for l in lengths])
    205 
    206 

ValueError: Found input variables with inconsistent numbers of samples: [2750, 1095]

Punjabi

Answer 1

Y = test['price'] should probably be Y = train['price'] (or whatever is the name of the feature).

The exception is raised because your X and Y have different number of samples (rows) and train_test_split doesn't like this.

Cheshire

thank you so much. Will keep in mind. Also, once the model is trained & fit, how to we use it to predict the values (in my case predicting the price) in the test samples? @Jan K – Punjabi

Something like regressor.predict(X_test) should work. Feel free to open a new question if some problems show up – Cheshire

not sure what the issue is with my current code that I am work, it contains only 1 data frame with both X & Y. using stratify to sample the data but I still get that error. – Approve

Answer 2

Encountered a similar error resolved it by transposing the input arrays:

X = np.transpose(np.stack((targetx, targety, targetz, target_r, target_d,target_b, target_t)))
Y = np.transpose(np.stack((x_target, y_target, z_target)))
regressor = LinearRegression()
regressor.fit(X, Y)

Mallen