data for a regression problem was provided to the TPOTClassifier object

[provide general introduction to the issue and why it is relevant to this repository]
I am testing TPOT with [Rossmann Sales](https://www.kaggle.com/c/rossmann-store-sales) data from Kaggle. The TPOT ends with error message:

> RuntimeError: There was an error in the TPOT optimization process. This could be because the data was not formatted properly, or because data for a regression problem was provided to the TPOTClassifier object. Please make sure you passed the data to TPOT correctly.

## Context of the issue
I am using TPOTRegressor as follow
`tpot = TPOTRegressor(scoring = 'neg_mean_absolute_error',
max_time_mins = 3,
n_jobs = -1,
verbosity = 2,
cv = 5,
config_dict=tpot_config)`
The max_time_mins is set to 3 in order to quickly debug. I have also tried 3-6 hours, still reports error.

I checked the label and feature shape.

`(844338,)`
`(844338, 29)`

So I am wondering where is the problem? I tried on MBP, CGP and Colab. All report error
## Process to reproduce the issue

[ordered list the process to finding and recreating the issue, example below]

1. User creates TPOT instance
2. User calls TPOT `fit()` function with training data
3. TPOT crashes with a `KeyError` after 5 generations

The notebook to reproduce the error can be found at https://colab.research.google.com/drive/19Y7uYyeyMiKlzp_fa6SB1lRSS6jI84wC#scrollTo=hhbitB9--XfC

It is a regression problem. I used the TPOT regressor. Even more I checked the feature and label/target shape.

## Expected result

TPOT ends with finding the best pipeline

## Current result

The Optimization process will complete while no pipeline is generated with error message as above.

## Possible fix

I have tried all possible solutions from https://github.com/EpistasisLab/tpot/issues/313. But the problem still remains.

## `name of issue` screenshot

[if relevant, include a screenshot]