added log files for these ml runs
This commit is contained in:
parent
5bd8ba33f7
commit
e176d018cb
20 changed files with 303568 additions and 0 deletions
75
scripts/ml/log_alr_8020.txt
Normal file
75
scripts/ml/log_alr_8020.txt
Normal file
|
@ -0,0 +1,75 @@
|
|||
/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_8020.py:549: SettingWithCopyWarning:
|
||||
A value is trying to be set on a copy of a slice from a DataFrame
|
||||
|
||||
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
|
||||
mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
|
||||
1.22.4
|
||||
1.4.1
|
||||
|
||||
aaindex_df contains non-numerical data
|
||||
|
||||
Total no. of non-numerial columns: 2
|
||||
|
||||
Selecting numerical data only
|
||||
|
||||
PASS: successfully selected numerical columns only for aaindex_df
|
||||
|
||||
Now checking for NA in the remaining aaindex_cols
|
||||
|
||||
Counting aaindex_df cols with NA
|
||||
ncols with NA: 4 columns
|
||||
Dropping these...
|
||||
Original ncols: 127
|
||||
|
||||
Revised df ncols: 123
|
||||
|
||||
Checking NA in revised df...
|
||||
|
||||
PASS: cols with NA successfully dropped from aaindex_df
|
||||
Proceeding with combining aa_df with other features_df
|
||||
|
||||
PASS: ncols match
|
||||
Expected ncols: 123
|
||||
Got: 123
|
||||
|
||||
Total no. of columns in clean aa_df: 123
|
||||
|
||||
Proceeding to merge, expected nrows in merged_df: 271
|
||||
|
||||
PASS: my_features_df and aa_df successfully combined
|
||||
nrows: 271
|
||||
ncols: 269
|
||||
count of NULL values before imputation
|
||||
|
||||
or_mychisq 256
|
||||
log10_or_mychisq 256
|
||||
dtype: int64
|
||||
count of NULL values AFTER imputation
|
||||
|
||||
mutationinformation 0
|
||||
or_rawI 0
|
||||
logorI 0
|
||||
dtype: int64
|
||||
|
||||
PASS: OR values imputed, data ready for ML
|
||||
|
||||
Total no. of features for aaindex: 123
|
||||
|
||||
No. of numerical features: 168
|
||||
No. of categorical features: 7
|
||||
|
||||
PASS: x_features has no target variable
|
||||
|
||||
No. of columns for x_features: 175
|
||||
Traceback (most recent call last):
|
||||
File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_8020.py", line 19, in <module>
|
||||
setvars(gene,drug)
|
||||
File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_8020.py", line 656, in setvars
|
||||
X, X_bts, y, y_bts = train_test_split(x_features, y_target
|
||||
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 2454, in train_test_split
|
||||
train, test = next(cv.split(X=arrays[0], y=stratify))
|
||||
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 1613, in split
|
||||
for train, test in self._iter_indices(X, y, groups):
|
||||
File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 1953, in _iter_indices
|
||||
raise ValueError(
|
||||
ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2.
|
Loading…
Add table
Add a link
Reference in a new issue