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

modified ml params and models

Browse source
This commit is contained in:
Tanushree Tunstall 2022-05-19 02:35:50 +01:00
parent 3ed7840f60
commit 4dbc90ad44
6 changed files with 17 additions and 332 deletions
Download patch file Download diff file Expand all files Collapse all files

11
MultClassPipe3.py
View file

@ -27,7 +27,7 @@ from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer from sklearn.compose import make_column_transformer
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score
from sklearn.metrics import make_scorer from sklearn.metrics import make_scorer
from sklearn.metrics import classification_report from sklearn.metrics import classification_report
@ -70,7 +70,7 @@ scoring_fn = ({ 'fscore' : make_scorer(f1_score)
, 'recall' : make_scorer(recall_score) , 'recall' : make_scorer(recall_score)
, 'accuracy' : make_scorer(accuracy_score) , 'accuracy' : make_scorer(accuracy_score)
, 'roc_auc' : make_scorer(roc_auc_score) , 'roc_auc' : make_scorer(roc_auc_score)
#, 'jaccard' : make_scorer(jaccard_score) , 'jaccard' : make_scorer(jaccard_score)
}) })
@ -122,10 +122,11 @@ def MultClassPipeSKFCV(input_df, target, skf_cv, var_type = ['numerical', 'categ
mlp = MLPClassifier(max_iter = 500, **rs) mlp = MLPClassifier(max_iter = 500, **rs)
dt = DecisionTreeClassifier(**rs) dt = DecisionTreeClassifier(**rs)
et = ExtraTreesClassifier(**rs) et = ExtraTreesClassifier(**rs)
rf = RandomForestClassifier(**rs) rf = RandomForestClassifier(**rs,
n_estimators = 1000 )
rf2 = RandomForestClassifier( rf2 = RandomForestClassifier(
min_samples_leaf = 50 min_samples_leaf = 5
, n_estimators = 150 , n_estimators = 1000
, bootstrap = True , bootstrap = True
, oob_score = True , oob_score = True
, **njobs , **njobs

257
UQ_imports_pnca.py
View file

@ -1,257 +0,0 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sun Mar 6 13:41:54 2022
@author: tanu
"""
import os, sys
import pandas as pd
import numpy as np
import pprint as pp
from copy import deepcopy
from sklearn import linear_model
from sklearn.linear_model import LogisticRegression, LinearRegression
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neural_network import MLPClassifier
from xgboost import XGBClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import SGDClassifier
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef
from sklearn.metrics import jaccard_score
from sklearn.metrics import make_scorer
from sklearn.metrics import classification_report
from sklearn.metrics import average_precision_score
from sklearn.model_selection import cross_validate
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.pipeline import Pipeline
from sklearn.pipeline import make_pipeline
from sklearn.feature_selection import RFE
from sklearn.feature_selection import RFECV
import itertools
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
print(np.__version__)
print(pd.__version__)
from statistics import mean, stdev, median, mode
from imblearn.over_sampling import RandomOverSampler
from imblearn.over_sampling import SMOTE
from imblearn.pipeline import Pipeline
#from sklearn.datasets import make_classification
from sklearn.model_selection import cross_validate, cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.ensemble import AdaBoostClassifier
from imblearn.combine import SMOTEENN
from imblearn.under_sampling import EditedNearestNeighbours
from sklearn.model_selection import GridSearchCV
from sklearn.base import BaseEstimator
scoring_fn = ({'accuracy' : make_scorer(accuracy_score)
, 'fscore' : make_scorer(f1_score)
, 'mcc' : make_scorer(matthews_corrcoef)
, 'precision' : make_scorer(precision_score)
, 'recall' : make_scorer(recall_score)
, 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score)
})
rs = {'random_state': 42}
njobs = {'n_jobs': 10}
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
, n_repeats=3
#, shuffle = False, random_state= None)
#, shuffle = True
,**rs)
#my_mcc = make_scorer({'mcc':make_scorer(matthews_corrcoef})
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
#%%
homedir = os.path.expanduser("~")
os.chdir(homedir + "/git/ML_AI_training/")
# my function
#from MultClassPipe import MultClassPipeline
from MultClassPipe2 import MultClassPipeline2
from loopity_loop import MultClassPipeSKFLoop
from MultClassPipe3 import MultClassPipeSKFCV
gene = 'pncA'
drug = 'pyrazinamide'
#==============
# directories
#==============
datadir = homedir + '/git/Data/'
indir = datadir + drug + '/input/'
outdir = datadir + drug + '/output/'
#=======
# input
#=======
infile_ml1 = outdir + gene.lower() + '_merged_df3.csv'
#infile_ml2 = outdir + gene.lower() + '_merged_df2.csv'
my_df = pd.read_csv(infile_ml1, index_col = 0)
my_df.dtypes
my_df_cols = my_df.columns
geneL_basic = ['pnca']
# -- CHECK script -- imports.py
#%% get cols
mycols = my_df.columns
mycols
# change from numberic to
num_type = ['int64', 'float64']
cat_type = ['object', 'bool']
# TODO:
# Treat active site aa pos as category and not numerical: This needs to be part of merged_df3!
#if my_df['active_aa_pos'].dtype in num_type:
# my_df['active_aa_pos'] = my_df['active_aa_pos'].astype(object)
# my_df['active_aa_pos'].dtype
# -- CHECK script -- imports.py
#%%============================================================================
#%% IMPUTE values for OR
#%% Combine mmCSM_lig Data
#%% Combine PROVEAN data
#%% Combine ED logo data
#%% Masking columns (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
# get logic from upstream!
my_df_ml = my_df.copy()
my_df_ml['mutationinformation'][my_df['ligand_distance']>10].value_counts()
my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
my_df_ml.groupby(['mutationinformation'])['ligand_distance'].apply(lambda x: (x>10)).value_counts()
my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), 'ligand_affinity_change'] = 0
(my_df_ml['ligand_affinity_change'] == 0).sum()
#%%============================================================================
# Separate blind test set
my_df_ml[drug].isna().sum()
blind_test_df = my_df_ml[my_df_ml[drug].isna()]
training_df = my_df_ml[my_df_ml[drug].notna()]
# Target1: dst
training_df[drug].value_counts()
training_df['dst_mode'].value_counts()
#%% Build X
common_cols_stabiltyN = ['ligand_distance'
, 'ligand_affinity_change'
, 'duet_stability_change'
, 'ddg_foldx'
, 'deepddg'
, 'ddg_dynamut2']
foldX_cols = ['contacts'
#, 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
#, 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss'
#, 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss'
#, 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss'
#, 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss'
#, 'volumetric_rr', 'volumetric_mm', 'volumetric_ss'
]
X_strFN = ['rsa'
#, 'asa'
, 'kd_values'
, 'rd_values']
X_evolFN = ['consurf_score'
, 'snap2_score']
# quick inspection which lineage to use:
#foo = my_df_ml[['lineage', 'lineage_count_all', 'lineage_count_unique']]
X_genomicFN = ['maf'
# , 'or_mychisq'
# , 'or_logistic'
# , 'or_fisher'
# , 'pval_fisher'
#, 'lineage'
, 'lineage_count_all'
, 'lineage_count_unique'
]
#%% Construct numerical and categorical column names
# numerical feature names
numerical_FN = common_cols_stabiltyN + foldX_cols + X_strFN + X_evolFN + X_genomicFN
#categorical feature names
categorical_FN = ['ss_class'
, 'wt_prop_water'
# , 'lineage_labels' # misleading if using merged_df3
, 'mut_prop_water'
, 'wt_prop_polarity'
, 'mut_prop_polarity'
, 'wt_calcprop'
, 'mut_calcprop'
#, 'active_aa_pos'
]
#%% extracting dfs based on numerical, categorical column names
#----------------------------------
# WITHOUT the target var included
#----------------------------------
num_df = training_df[numerical_FN]
num_df.shape
cat_df = training_df[categorical_FN]
cat_df.shape
all_df = training_df[numerical_FN + categorical_FN]
all_df.shape
#------------------------------
# WITH the target var included:
#'wtgt': with target
#------------------------------
# drug and dst_mode should be the same thing
num_df_wtgt = training_df[numerical_FN + ['dst_mode']]
num_df_wtgt.shape
cat_df_wtgt = training_df[categorical_FN + ['dst_mode']]
cat_df_wtgt.shape
all_df_wtgt = training_df[numerical_FN + categorical_FN + ['dst_mode']]
all_df_wtgt.shape
#%%================================================================
#%% Apply ML

56
UQ_pnca_ml_CALL.py
View file

@ -1,56 +0,0 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon May 16 05:59:12 2022
@author: tanu
"""
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Mar 15 11:09:50 2022
@author: tanu
"""
#%% Data
X = all_df_wtgt[numerical_FN+categorical_FN]
X = all_df_wtgt[numerical_FN]
y = all_df_wtgt['dst_mode']
#%% variables
#%% MultClassPipeSKFCV: function call()
mm_skf_scoresD = MultClassPipeSKFCV(input_df = X
, target = y
, var_type = 'numerical'
, skf_cv = skf_cv)
mm_skf_scores_df_all = pd.DataFrame(mm_skf_scoresD)
mm_skf_scores_df_all
mm_skf_scores_df_test = mm_skf_scores_df_all.filter(like='test_', axis=0)
mm_skf_scores_df_train = mm_skf_scores_df_all.filter(like='train_', axis=0) # helps to see if you trust the results
#%% CHECK with BLIND test
#%%
import plotly.express as px
corr = X.corr(method = 'spearman')
corr.head()
#p = corr.style.background_gradient(cmap='coolwarm')
p = corr.style.background_gradient(cmap='coolwarm').set_precision(2)
p
fig = px.imshow(corr)
fig.show()
#%%TODO:
# Add correlation plot
# Remove low variance features
# Add feature selection
# Then run your models on BLIND test WITHOUT CV

BIN
__pycache__/MultClassPipe3.cpython-37.pyc
View file

Binary file not shown.

13
base_estimator3.py
View file

@ -17,16 +17,11 @@ from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from xgboost import XGBClassifier from xgboost import XGBClassifier
#%% Get train-test split and scoring functions #######################################################
X_train, X_test, y_train, y_test = train_test_split(num_df_wtgt[numerical_FN] y.to_frame().value_counts().plot(kind = 'bar')
, num_df_wtgt['mutation_class']
, test_size = 0.33 blind_test_df['dst_mode'].to_frame().value_counts().plot(kind = 'bar')
, random_state = 2
, shuffle = True
, stratify = num_df_wtgt['mutation_class'])
y_train.to_frame().value_counts().plot(kind = 'bar')
y_test.to_frame().value_counts().plot(kind = 'bar')
scoring_fn = ({'accuracy' : make_scorer(accuracy_score) scoring_fn = ({'accuracy' : make_scorer(accuracy_score)
, 'fscore' : make_scorer(f1_score) , 'fscore' : make_scorer(f1_score)
, 'mcc' : make_scorer(matthews_corrcoef) , 'mcc' : make_scorer(matthews_corrcoef)

12
classification_names_params.py
View file

@ -32,7 +32,7 @@ names = [
] ]
classifiers = [ classifiers = [
KNeighborsClassifier(3), KNeighborsClassifier(5),
SVC(kernel="linear", C=0.025), SVC(kernel="linear", C=0.025),
SVC(gamma=2, C=1), SVC(gamma=2, C=1),
GaussianProcessClassifier(1.0 * RBF(1.0)), GaussianProcessClassifier(1.0 * RBF(1.0)),
@ -97,7 +97,7 @@ classifiers = [
)) ))
gs_knn_params = { gs_knn_params = {
'clf__n_neighbors': [3, 7, 10] 'clf__n_neighbors': [5, 7, 11]
#, 'clf__n_neighbors': range(1, 21, 2) #, 'clf__n_neighbors': range(1, 21, 2)
,'clf__metric' : ['euclidean', 'manhattan', 'minkowski'] ,'clf__metric' : ['euclidean', 'manhattan', 'minkowski']
, 'clf__weights' : ['uniform', 'distance'] , 'clf__weights' : ['uniform', 'distance']
@ -120,7 +120,7 @@ classifiers = [
, 'clf__min_samples_leaf': [2, 4, 8, 50] , 'clf__min_samples_leaf': [2, 4, 8, 50]
, 'clf__min_samples_split': [10, 20] , 'clf__min_samples_split': [10, 20]
} }
#%% XGBClassifier() #%% XGBClassifier() # SPNT
# https://stackoverflow.com/questions/34674797/xgboost-xgbclassifier-defaults-in-python # https://stackoverflow.com/questions/34674797/xgboost-xgbclassifier-defaults-in-python
# https://stackoverflow.com/questions/34674797/xgboost-xgbclassifier-defaults-in-python # https://stackoverflow.com/questions/34674797/xgboost-xgbclassifier-defaults-in-python
gs_xgb = Pipeline(( gs_xgb = Pipeline((
@ -135,6 +135,7 @@ classifiers = [
, 'clf__min_samples_leaf': [4, 8, 12, 16, 20] , 'clf__min_samples_leaf': [4, 8, 12, 16, 20]
, 'clf__max_features': ['auto', 'sqrt'] , 'clf__max_features': ['auto', 'sqrt']
} }
#%% MLPClassifier() #%% MLPClassifier()
# https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html # https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html
gs_mlp = Pipeline(( gs_mlp = Pipeline((
@ -190,6 +191,7 @@ classifiers = [
# If None, then the base estimator is a DecisionTreeClassifier. # If None, then the base estimator is a DecisionTreeClassifier.
, 'clf__base_estimator' : ['None', 'SVC()', 'KNeighborsClassifier()']# if none, DT is used , 'clf__base_estimator' : ['None', 'SVC()', 'KNeighborsClassifier()']# if none, DT is used
, 'clf__gamma': ['scale', 'auto'] } , 'clf__gamma': ['scale', 'auto'] }
#%% GradientBoostingClassifier() #%% GradientBoostingClassifier()
# https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingClassifier.html # https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingClassifier.html
gs_gb = Pipeline(( gs_gb = Pipeline((
@ -198,7 +200,7 @@ classifiers = [
)) ))
gs_bdt_params = { gs_bdt_params = {
'clf__n_estimators' : [10, 100, 1000] 'clf__n_estimators' : [10, 100, 200, 500, 1000]
, 'clf__n_estimators' : [10, 100, 1000] , 'clf__n_estimators' : [10, 100, 1000]
, 'clf__learning_rate': [0.001, 0.01, 0.1] , 'clf__learning_rate': [0.001, 0.01, 0.1]
, 'clf__subsample' : [0.5, 0.7, 1.0] , 'clf__subsample' : [0.5, 0.7, 1.0]
@ -261,4 +263,4 @@ BernoulliNB(alpha=1.0, binarize=0.0, class_prior=None, fit_prior=True)
, 'clf__binarize':['None', 0] , 'clf__binarize':['None', 0]
, 'clf__fit_prior': [True] , 'clf__fit_prior': [True]
, 'clf__class_prior': ['None'] , 'clf__class_prior': ['None']
} }