tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

saving work

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-29 00:12:43 +01:00
parent 1695e90b42
commit e55906d2c7
3 changed files with 11 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

13
scripts/ml/combined_model/cm_logo_skf.py
View file

@ -139,9 +139,9 @@ def CMLogoSkf(cm_input_df
# else:
# file_suffix = file_suffix
outFile = output_dir + str(n_tr_genes+1) + "genes_" + tts_split_type + '_' + file_suffix + ".csv"
#outFile = output_dir + str(n_tr_genes+1) + "genes_" + tts_split_type + '_' + file_suffix + ".csv"
print(outFile)
#print(outFile)
#-------
# training
@ -175,6 +175,7 @@ def CMLogoSkf(cm_input_df
, '\nTEST Target dim:' , cm_bts_y.shape)
print("Running Multiple models on LOGO with SKF")
#%%:Running Multiple models on LOGO with SKF
# cD3_v2 = MultModelsCl_logo_skf(input_df = cm_X # two func were identical excpet for name
cD3_v2 = MultModelsCl(input_df = cm_X
@ -203,11 +204,11 @@ def CMLogoSkf(cm_input_df
#===============
# Complete Data
#===============
CMLogoSkf(cm_input_df = combined_df,file_suffix = "complete")
CMLogoSkf(cm_input_df = combined_df, std_gene_omit=['alr'], file_suffix = "complete")
#CMLogoSkf(cm_input_df = combined_df,file_suffix = "complete")
#CMLogoSkf(cm_input_df = combined_df, std_gene_omit=['alr'], file_suffix = "complete")
#===============
# Actual Data
#===============
CMLogoSkf(cm_input_df = combined_df_actual, file_suffix = "actual")
CMLogoSkf(cm_input_df = combined_df_actual, std_gene_omit=['alr'], file_suffix = "actual")
#CMLogoSkf(cm_input_df = combined_df_actual, file_suffix = "actual")
#CMLogoSkf(cm_input_df = combined_df_actual, std_gene_omit=['alr'], file_suffix = "actual")

4
scripts/ml/ml_functions/SplitTTS.py
View file

@ -269,7 +269,9 @@ def split_tts(ml_input_data
#k_sm = 5 # default
k_sm = k_smote
sm_nc = SMOTENC(categorical_features=categorical_colind, k_neighbors = k_sm, **rs, **njobs)
sm_nc = SMOTENC(categorical_features=categorical_colind
, k_neighbors = k_sm
, **rs, **njobs)
X_smnc, y_smnc = sm_nc.fit_resample(X, y)
print('\nSMOTE_NC OverSampling\n', Counter(y_smnc))
print(X_smnc.shape)

2
scripts/ml/ml_functions/ml_data_combined.py
View file

@ -54,6 +54,7 @@ expected_ncols
if len(common_cols) == expected_ncols:
print('\nProceeding to combine based on common cols (n):', len(common_cols))
combined_df = pd.concat([df[common_cols] for df in dfs_combine], ignore_index = False)
print('\nSuccessfully combined dfs:'
, '\nNo. of dfs combined:', len(dfs_combine)
, '\nDim of combined df:', combined_df.shape)
@ -76,7 +77,6 @@ cm_input_df5 = combined_df[~combined_df['gene_name'].isin(omit_gene_alr)]
combined_df['dst'].isna().sum()
combined_df['dst'].value_counts().sum()
combined_df_actual = combined_df[~combined_df['dst'].isna()]
##############################################################################