Unittest errors with new version of sklearn

[isaacmg]

As many of you know sklearn recently upgraded to 1.0 from 0.24. The newer version generate two errors related to failing unit tests. These should be investigated and fixed.

raceback (most recent call last):
  File "/home/circleci/repo/tests/test_deployment.py", line 39, in test_infer_multi
    save_name="tes1/t2.csv", wandb_plot_id="prod_plot")
  File "/home/circleci/repo/flood_forecast/deployment/inference.py", line 106, in make_plots
    df, tensor, history, forecast_start, test, samples = self.infer_now(date, csv_path, csv_bucket, save_name)
  File "/home/circleci/repo/flood_forecast/deployment/inference.py", line 71, in infer_now
    unscaled = test.inverse_scale(tensor.numpy())
  File "/home/circleci/repo/flood_forecast/preprocessing/pytorch_loaders.py", line 150, in inverse_scale
    self.targ_scaler.inverse_transform(result_data_np)
  File "/usr/local/lib/python3.7/site-packages/sklearn/preprocessing/_data.py", line 1022, in inverse_transform
    force_all_finite="allow-nan",
  File "/usr/local/lib/python3.7/site-packages/sklearn/utils/validation.py", line 788, in check_array
    % (array.ndim, estimator_name)
ValueError: Found array with dim 3. StandardScaler expected <= 2.

Traceback (most recent call last):
  File "/home/circleci/repo/tests/pytorc_train_tests.py", line 304, in test_scaling_data
    inverse_scale = self.model.test_data.inverse_scale(scaled_src[:, 0])
  File "/home/circleci/repo/flood_forecast/preprocessing/pytorch_loaders.py", line 150, in inverse_scale
    self.targ_scaler.inverse_transform(result_data_np)
  File "/usr/local/lib/python3.7/site-packages/sklearn/preprocessing/_data.py", line 1022, in inverse_transform
    force_all_finite="allow-nan",
  File "/usr/local/lib/python3.7/site-packages/sklearn/utils/validation.py", line 765, in check_array
    "if it contains a single sample.".format(array)
ValueError: Expected 2D array, got 1D array instead:
array=[0.6595671  0.6595671  0.64500946 0.6595671  0.68504316 0.6959614
 0.7359951  0.7760289  0.81606257 0.870654   0.9288848  0.9834762
 1.0671831  1.1545293  1.2564334  1.3619767  1.482078   1.6240156
 1.7659533  1.9115304 ].
Reshape your data either using ar

[isaacmg]

I think they likely added additional checks on data dimensions which is why this is failing.

[isaacmg]

See #414