144 lines
No EOL
4.9 KiB
Python
144 lines
No EOL
4.9 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Sat Mar 5 12:57:32 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
#%%
|
|
# data, etc for now comes from my_data6.py and/or my_data5.py
|
|
#%% try combinations
|
|
#import sys, os
|
|
#os.system("imports.py")
|
|
def precision(y_true,y_pred):
|
|
return precision_score(y_true,y_pred,pos_label = 1)
|
|
def recall(y_true,y_pred):
|
|
return recall_score(y_true, y_pred, pos_label = 1)
|
|
def f1(y_true,y_pred):
|
|
return f1_score(y_true, y_pred, pos_label = 1)
|
|
|
|
#%%
|
|
numerical_features_df.shape
|
|
categorical_features_df.shape
|
|
all_features_df.shape
|
|
#%%
|
|
target = target1
|
|
#target = target3
|
|
X_trainN, X_testN, y_trainN, y_testN = train_test_split(numerical_features_df,
|
|
target,
|
|
test_size = 0.33,
|
|
random_state = 42)
|
|
|
|
X_trainC, X_testC, y_trainC, y_testC = train_test_split(categorical_features_df,
|
|
target,
|
|
test_size = 0.33,
|
|
random_state = 42)
|
|
|
|
X_train, X_test, y_train, y_test = train_test_split(all_features_df,
|
|
target,
|
|
test_size = 0.33,
|
|
random_state = 42)
|
|
#%%
|
|
|
|
#%%
|
|
preprocessor = ColumnTransformer(
|
|
transformers=[
|
|
('num', MinMaxScaler() , numerical_features_names)
|
|
,('cat', OneHotEncoder(), categorical_features_names)
|
|
], remainder = 'passthrough')
|
|
|
|
f = preprocessor.fit(numerical_features_df)
|
|
f2 = preprocessor.transform(numerical_features_df)
|
|
|
|
f3 = preprocessor.fit_transform(numerical_features_df)
|
|
(f3==f2).all()
|
|
|
|
preprocessor.fit_transform(numerical_features_df)
|
|
|
|
#preprocessor.fit_transform(all_features_df)
|
|
|
|
#%%
|
|
model_log = Pipeline(steps = [
|
|
('preprocess', preprocessor)
|
|
#,('log_reg', linear_model.LogisticRegression())
|
|
,('log_reg', LogisticRegression(
|
|
class_weight = 'unbalanced'))
|
|
])
|
|
model = model_log
|
|
#%%
|
|
seed = 42
|
|
model_rf = Pipeline(steps = [
|
|
('preprocess', preprocessor)
|
|
,('rf', RandomForestClassifier(
|
|
min_samples_leaf=50,
|
|
n_estimators=150,
|
|
bootstrap=True,
|
|
oob_score=True,
|
|
n_jobs=-1,
|
|
random_state=seed,
|
|
max_features='auto'))
|
|
])
|
|
model = model_rf
|
|
#%%
|
|
model.fit(X_trainN, y_trainN)
|
|
y_pred = model.predict(X_testN)
|
|
y_pred
|
|
|
|
acc = make_scorer(accuracy_score)
|
|
prec = make_scorer(precision)
|
|
rec = make_scorer(recall)
|
|
f1 = make_scorer(f1)
|
|
|
|
output = cross_validate(model, X_trainN, y_trainN
|
|
, scoring = {'acc' : acc
|
|
,'prec': prec
|
|
,'rec' : rec
|
|
,'f1' : f1}
|
|
, cv = 10
|
|
, return_train_score = False)
|
|
pd.DataFrame(output).mean()
|
|
#%% Run multiple models using MultClassPipeline
|
|
# only good for numerical features as categ features is not supported yet!
|
|
t1_res = MultClassPipeline2(X_trainN, X_testN, y_trainN, y_testN, input_df = all_features_df)
|
|
t1_res
|
|
|
|
#%%
|
|
# https://machinelearningmastery.com/columntransformer-for-numerical-and-categorical-data/
|
|
#Each transformer is a three-element tuple that defines the name of the transformer, the transform to apply, and the column indices to apply it to. For example:
|
|
# (Name, Object, Columns)
|
|
|
|
# Determine categorical and numerical features
|
|
numerical_ix = all_features_df.select_dtypes(include=['int64', 'float64']).columns
|
|
numerical_ix
|
|
categorical_ix = all_features_df.select_dtypes(include=['object', 'bool']).columns
|
|
categorical_ix
|
|
|
|
# Define the data preparation for the columns
|
|
t = [('cat', OneHotEncoder(), categorical_ix)
|
|
, ('num', MinMaxScaler(), numerical_ix)]
|
|
col_transform = ColumnTransformer(transformers=t
|
|
, remainder='passthrough')
|
|
# create pipeline (unlike example above where the col transfer was a preprocess step and it was fit_transformed)
|
|
|
|
pipeline = Pipeline(steps=[('prep', col_transform)
|
|
, ('classifier', LogisticRegression())])
|
|
#%% Added this to the MultClassPipeline
|
|
|
|
tN_res = MultClassPipeline(X_trainN, X_testN, y_trainN, y_testN)
|
|
tN_res
|
|
|
|
t2_res = MultClassPipeline2(X_train, X_test, y_train, y_test, input_df = all_features_df)
|
|
t2_res
|
|
|
|
t3_res = MultClassPipeSKF(input_df = numerical_features_df
|
|
, y_targetF = target1
|
|
, var_type = 'numerical'
|
|
, skf_splits = 10)
|
|
t3_res
|
|
|
|
|
|
t4_res = MultClassPipeSKF(input_df = all_features_df
|
|
, y_targetF = target1
|
|
, var_type = 'mixed'
|
|
, skf_splits = 10)
|
|
t4_res |