[Tutor] ValueError: Unable to coerce to DataFrame, shape must be (842, 1): given (3367, 1); ValueError: cannot reshape array of size 1 into shape (4)

[Alan Gauld]

On 29/03/2021 08:04, Anosh Kaniskar wrote:

Hi Anosh,
The tutor list is focused on the Python language and its standard
library. This question seems to be entirely about sklearn and Pandas
so you might get a better result asking on the SciPy forum which
supports Pandas.

However, there are some pandas users here so you may get lucky...

> So, before using any model, i performed pca technique to deal with the
> curse of dimensionality, and I started with the multiple linear regression
> model and Im not satisfied with the outcome, so I started using Random
> Forest and I successfully fitted the data on to the random forest model
> for eg:
> from sklearn.ensemble import RandomForestRegressor
> RFReg = RandomForestRegressor(n_estimators=500,max_depth=4, random_state =
> 50)
> RFReg.fit(X_train, y_train)
> 
> y_pred_train = RFReg.predict(X_train)
> y_pred_train
> ____________________________________________
> errors = abs(y_test - y_pred_train)
> errors
> This code gave me an error
> 
> ~/Desktop/Desktop/anaconda3/lib/python3.8/site-packages/pandas/core/ops/__init__.py
> in _align_method_FRAME(left, right, axis)    661     662
> else:--> 663                 raise ValueError(    664
>    "Unable to coerce to DataFrame, shape "    665
> f"must be {left.shape}: given {right.shape}"
> 
> 
> ValueError: Unable to coerce to DataFrame, shape must be (842, 1):
> given (3367, 1)
> 
> _______________________________________________
> 
> 
> So later I tried
> 
> y_pred_train = y_pred_train.reshape(3367, 1)
> 
> 
> Here I'm looking for explanation for what is going wrong..


-- 
Alan G
Author of the Learn to Program web site
http://www.alan-g.me.uk/
http://www.amazon.com/author/alan_gauld
Follow my photo-blog on Flickr at:
http://www.flickr.com/photos/alangauldphotos