On 12/18/2014 02:24 PM, Lars Buitinck wrote: > 2014-12-18 20:14 GMT+01:00 David Brough <david.brough.0...@gmail.com>: >> Thank you for the quick response. >> I currently using version 0.15.2. Our arrays have dimensions [n_samples, x, >> y, z]. Below are the two trace-backs I get for both train_test_split and >> GrindSearchCV. They both end at the same line of code. > The dimensions for feature matrices have always been documented as > (n_samples, n_features), and newer versions are stricter at enforcing > this to catch bugs early on (error messages were unreadable if they > came from deep within the code). If you need other shapes, you should > reshape at the boundary. > I'm pretty sure currently there is less restrictions, which makes sense for the gridsearch and cross-validation. In GridSearchCV it should always be allowed. In train_test_split there was an allow_nd argument in there, but I think it is now enabled by default.
------------------------------------------------------------------------------ Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server from Actuate! Instantly Supercharge Your Business Reports and Dashboards with Interactivity, Sharing, Native Excel Exports, App Integration & more Get technology previously reserved for billion-dollar corporations, FREE http://pubads.g.doubleclick.net/gampad/clk?id=164703151&iu=/4140/ostg.clktrk _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
