def main():
# Load the diabetes sample data
dataframe = hcai_datasets.load_diabetes()
# ## Load data from a MSSQL server: Uncomment to pull data from MSSQL server
# server = 'localhost'
# database = 'SAM'
# query = """SELECT *
# FROM [SAM].[dbo].[DiabetesClincialSampleData]
# -- In this step, just grab rows that have a target
# WHERE ThirtyDayReadmitFLG is not null"""
#
# engine = hcai_db.build_mssql_engine(server=server, database=database)
# dataframe = pd.read_sql(query, engine)
# Drop columns that won't help machine learning
dataframe.drop(['PatientID'], axis=1, inplace=True)
# Step 1: Setup a healthcareai classification trainer. This prepares your data for model building
classification_trainer = SupervisedModelTrainer(
dataframe=dataframe,
predicted_column='ThirtyDayReadmitFLG',
model_type='classification',
grain_column='PatientEncounterID',
impute=True,
verbose=False)
# Look at the first few rows of your dataframe after loading the data
print(
'\n\n-------------------[ Cleaned Dataframe ]--------------------------'
)
print(classification_trainer.clean_dataframe.head())
# Step 2: train some models
# Train a KNN model
trained_knn = classification_trainer.knn()
# View the ROC and PR plots
trained_knn.roc_plot()
trained_knn.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_knn.roc()
# trained_knn.pr()
# Train a logistic regression model
trained_lr = classification_trainer.logistic_regression()
# View the ROC and PR plots
trained_lr.roc_plot()
trained_lr.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_lr.roc()
# trained_lr.pr()
# Train a random forest model and view the feature importance plot
trained_random_forest = classification_trainer.random_forest(
save_plot=False)
# View the ROC and PR plots
trained_random_forest.roc_plot()
trained_random_forest.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_random_forest.roc()
# trained_random_forest.pr()
# Create a list of all the models you just trained that you want to compare
models_to_compare = [trained_knn, trained_lr, trained_random_forest]
# Create a ROC plot that compares them.
tsm_plots.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='ROC',
save=False)
# Create a PR plot that compares them.
tsm_plots.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='PR',
save=False)
# Once you are happy with the performance of any model, you can save it for use later in predicting new data.
# File names are timestamped and look like '2017-05-31T12-36-21_classification_RandomForestClassifier.pkl')
# Note the file you saved and that will be used in example_classification_2.py
trained_random_forest.save()
def main():
"""Template script for ADVANCED USERS using healthcareai."""
# Load the included diabetes sample data
dataframe = healthcareai.load_diabetes()
# ...or load your own data from a .csv file: Uncomment to pull data from your CSV
# dataframe = healthcareai.load_csv('path/to/your.csv')
# ...or load data from a MSSQL server: Uncomment to pull data from MSSQL server
# server = 'localhost'
# database = 'SAM'
# query = """SELECT *
# FROM [SAM].[dbo].[DiabetesClincialSampleData]
# -- In this step, just grab rows that have a target
# WHERE ThirtyDayReadmitFLG is not null"""
#
# engine = hcai_db.build_mssql_engine_using_trusted_connections(server=server, database=database)
# dataframe = pd.read_sql(query, engine)
# Peek at the first 5 rows of data
print(dataframe.head(5))
# Drop columns that won't help machine learning
dataframe.drop(['PatientID'], axis=1, inplace=True)
# Step 1: Prepare the data using optional imputation. There are two options for this:
# ## Option 1: Use built in data prep pipeline that does enocding, imputation, null filtering, dummification
clean_training_dataframe = hcai_pipelines.full_pipeline(
'classification',
'ThirtyDayReadmitFLG',
'PatientEncounterID',
impute=True).fit_transform(dataframe)
# ## Option 2: Build your own pipeline using healthcare.ai methods, your own, or a combination of either.
# - Please note this is intentionally spartan, so we don't hinder your creativity. :)
# - Also note that many of the healthcare.ai transformers intentionally return dataframes, compared to scikit that
# return numpy arrays
# custom_pipeline = Pipeline([
# ('remove_grain_column', hcai_filters.DataframeColumnRemover(columns_to_remove=['PatientEncounterID', 'PatientID'])),
# ('imputation', hcai_transformers.DataFrameImputer(impute=True)),
# ('convert_target_to_binary', hcai_transformers.DataFrameConvertTargetToBinary('classification', 'ThirtyDayReadmitFLG')),
# # ('prediction_to_numeric', hcai_transformers.DataFrameConvertColumnToNumeric('ThirtyDayReadmitFLG')),
# # ('create_dummy_variables', hcai_transformers.DataFrameCreateDummyVariables(excluded_columns=['ThirtyDayReadmitFLG'])),
# ])
#
# clean_training_dataframe = custom_pipeline.fit_transform(dataframe)
# Step 2: Instantiate an Advanced Trainer class with your clean and prepared training data
classification_trainer = healthcareai.AdvancedSupervisedModelTrainer(
dataframe=clean_training_dataframe,
model_type='classification',
predicted_column='ThirtyDayReadmitFLG',
grain_column='PatientEncounterID',
verbose=False)
# Step 3: split the data into train and test
classification_trainer.train_test_split()
# Step 4: Train some models
# ## Train a KNN classifier with a randomized search over custom hyperparameters
knn_hyperparameters = {
'algorithm': ['ball_tree', 'kd_tree'],
'n_neighbors': [1, 4, 6, 8, 10, 15, 20, 30, 50, 100, 200],
'weights': ['uniform', 'distance']
}
trained_knn = classification_trainer.knn(
scoring_metric='accuracy',
hyperparameter_grid=knn_hyperparameters,
randomized_search=True,
# Set this relative to the size of your hyperparameter space. Higher will train more models and be slower
# Lower will be faster and possibly less performant
number_iteration_samples=10)
# ## Train a random forest classifier with a randomized search over custom hyperparameters
# TODO these are bogus hyperparams for random forest
random_forest_hyperparameters = {
'n_estimators': [50, 100, 200, 300],
'max_features': [1, 2, 3, 4],
'max_leaf_nodes': [None, 30, 400]
}
trained_random_forest = classification_trainer.random_forest_classifier(
scoring_metric='accuracy',
hyperparameter_grid=random_forest_hyperparameters,
randomized_search=True,
# Set this relative to the size of your hyperparameter space. Higher will train more models and be slower
# Lower will be faster and possibly less performant
number_iteration_samples=10)
# Show the random forest feature importance graph
hcai_tsm.plot_rf_features_from_tsm(trained_random_forest,
classification_trainer.x_train,
feature_limit=20,
save=False)
# ## Train a custom ensemble of models
# The ensemble methods take a dictionary of TrainedSupervisedModels by a name of your choice
custom_ensemble = {
'KNN':
classification_trainer.knn(hyperparameter_grid=knn_hyperparameters,
randomized_search=False,
scoring_metric='roc_auc'),
'Logistic Regression':
classification_trainer.logistic_regression(),
'Random Forest Classifier':
classification_trainer.random_forest_classifier(
randomized_search=False, scoring_metric='roc_auc')
}
trained_ensemble = classification_trainer.ensemble_classification(
scoring_metric='roc_auc', trained_model_by_name=custom_ensemble)
# Step 5: Evaluate and compare the models
# Create a list of all the models you just trained that you want to compare
models_to_compare = [trained_knn, trained_random_forest, trained_ensemble]
# Create a ROC plot that compares all the them.
hcai_tsm.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='ROC',
save=False)
# Create a PR plot that compares all the them.
hcai_tsm.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='PR',
save=False)
# Inspect the raw ROC or PR cutoffs
print(trained_random_forest.roc(print_output=False))
print(trained_random_forest.pr(print_output=False))
def main():
"""Template script for using healthcareai to train a classification model."""
# Load the included diabetes sample data
# dataframe = healthcareai.load_cervical()
# ...or load your own data from a .csv file: Uncomment to pull data from your CSV
dataframe = healthcareai.load_csv(
'./healthcareai/datasets/data/diagnostic_breast_cancer.csv')
# ...or load data from a MSSQL server: Uncomment to pull data from MSSQL server
# server = 'localhost'
# database = 'SAM'
# query = """SELECT *
# FROM [SAM].[dbo].[DiabetesClincialSampleData]
# -- In this step, just grab rows that have a target
# WHERE ThirtyDayReadmitFLG is not null"""
#
# engine = hcai_db.build_mssql_engine_using_trusted_connections(server=server, database=database)
# dataframe = pd.read_sql(query, engine)
# Peek at the first 5 rows of data
print(dataframe.head(5))
# Drop columns that won't help machine learning
# dataframe.drop(['PatientID'], axis=1, inplace=True)
# Step 1: Setup a healthcareai classification trainer. This prepares your data for model building
classification_trainer = healthcareai.SupervisedModelTrainer(
dataframe=dataframe,
predicted_column='Diagnosis',
model_type='classification',
grain_column='ID',
impute=False,
verbose=False)
"""
The below code demonstrate the advance features for imputation of missing values.
imputeStrategy:
'MeanMode': (default), Impute using mean and mode values of column
'RandomForest': Impute missing values in RandomForest models.(Imputed values are much more realistic)
tunedRandomForest:
True: ML to be used for imputation of missing values are tuned using grid search and K-fold cross
validation.
numeric_columns_as_categorical :
For example: GenderFLG (0,0,1,0,1,1 .... )
So in normal case pandas by default will consider this column as numeric and missing values of this column
will be imputed using MEAN value (ex. 0.78 or 1.46 ....).
Thus to explicitly mention such as categorical there is this option which can be used as below:
numeric_columns_as_categorical = 'GenderFLG'
Now imputation will be done by MODE value and final type of the column wil be np.object.
"""
# Uncomment below code to see advance imputation in action.
"""
# Creating missing values in GenderFLG column and converting it into Numeric type to demostrate advance imputation features.
dataframe['GenderFLG'].iloc[ 500:530, ] = np.NaN
dataframe['GenderFLG'].replace( to_replace=[ 'M', 'F' ], value=[ 0, 1], inplace=True )
pd.options.mode.chained_assignment = None
classification_trainer = healthcareai.SupervisedModelTrainer(
dataframe=dataframe,
predicted_column='ThirtyDayReadmitFLG',
model_type='classification',
grain_column='PatientEncounterID',
impute=True,
verbose=False,
imputeStrategy = 'RandomForest',
tunedRandomForest = True,
numeric_columns_as_categorical = 'GenderFLG'
)
"""
# Look at the first few rows of your dataframe after loading the data
print(
'\n\n-------------------[ Cleaned Dataframe ]--------------------------'
)
print(classification_trainer.clean_dataframe.head())
# Step 2: train some models
# Train a KNN model
trained_knn = classification_trainer.knn()
# View the ROC and PR plots
trained_knn.roc_plot()
trained_knn.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_knn.roc()
# trained_knn.pr()
# Train a logistic regression model
trained_lr = classification_trainer.logistic_regression()
# View the ROC and PR plots
trained_lr.roc_plot()
trained_lr.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_lr.roc()
# trained_lr.pr()
# Train a random forest model and view the feature importance plot
trained_random_forest = classification_trainer.random_forest(
save_plot=False)
# View the ROC and PR plots
trained_random_forest.roc_plot()
trained_random_forest.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_random_forest.roc()
# trained_random_forest.pr()
# Create a list of all the models you just trained that you want to compare
models_to_compare = [trained_knn, trained_lr, trained_random_forest]
# Create a ROC plot that compares them.
tsm_plots.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='ROC',
save=False)
# Create a PR plot that compares them.
tsm_plots.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='PR',
save=False)
# Once you are happy with the performance of any model, you can save it for use later in predicting new data.
# File names are timestamped and look like '2017-05-31T12-36-21_classification_RandomForestClassifier.pkl')
# Note the file you saved and that will be used in example_classification_2.py
trained_random_forest.save()
def main():
"""Template script for ADVANCED USERS using healthcareai."""
# Load the included diabetes sample data
dataframe = healthcareai.load_diabetes()
# ...or load your own data from a .csv file: Uncomment to pull data from your CSV
# dataframe = healthcareai.load_csv('path/to/your.csv')
# ...or load data from a MSSQL server: Uncomment to pull data from MSSQL server
# server = 'localhost'
# database = 'SAM'
# query = """SELECT *
# FROM [SAM].[dbo].[DiabetesClincialSampleData]
# -- In this step, just grab rows that have a target
# WHERE ThirtyDayReadmitFLG is not null"""
#
# engine = hcai_db.build_mssql_engine_using_trusted_connections(server=server, database=database)
# dataframe = pd.read_sql(query, engine)
# Peek at the first 5 rows of data
print(dataframe.head(5))
# Drop columns that won't help machine learning
dataframe.drop(['PatientID'], axis=1, inplace=True)
# Step 1: Prepare the data using optional imputation. There are two options for this:
# ## Option 1: Use built in data prep pipeline that does enocding, imputation, null filtering, dummification
clean_training_dataframe = hcai_pipelines.full_pipeline(
'classification',
'ThirtyDayReadmitFLG',
'PatientEncounterID',
impute=True).fit_transform(dataframe)
# ## Option 2: Build your own pipeline using healthcare.ai methods, your own, or a combination of either.
# - Please note this is intentionally spartan, so we don't hinder your creativity. :)
# - Also note that many of the healthcare.ai transformers intentionally return dataframes, compared to scikit that
# return numpy arrays
# custom_pipeline = Pipeline([
# ('remove_grain_column', hcai_filters.DataframeColumnRemover(columns_to_remove=['PatientEncounterID', 'PatientID'])),
# ('imputation', hcai_transformers.DataFrameImputer(impute=True)),
# ('convert_target_to_binary', hcai_transformers.DataFrameConvertTargetToBinary('classification', 'ThirtyDayReadmitFLG')),
# # ('prediction_to_numeric', hcai_transformers.DataFrameConvertColumnToNumeric('ThirtyDayReadmitFLG')),
# # ('create_dummy_variables', hcai_transformers.DataFrameCreateDummyVariables(excluded_columns=['ThirtyDayReadmitFLG'])),
# ])
#
# clean_training_dataframe = custom_pipeline.fit_transform(dataframe)
# Step 2: Instantiate an Advanced Trainer class with your clean and prepared training data
classification_trainer = healthcareai.AdvancedSupervisedModelTrainer(
dataframe=clean_training_dataframe,
model_type='classification',
predicted_column='ThirtyDayReadmitFLG',
grain_column='PatientEncounterID',
verbose=False)
# Step 3: split the data into train and test
classification_trainer.train_test_split()
# Step 4: Train some models
# ## Train a KNN classifier with a randomized search over custom hyperparameters
knn_hyperparameters = {
'algorithm': ['ball_tree', 'kd_tree'],
'n_neighbors': [1, 4, 6, 8, 10, 15, 20, 30, 50, 100, 200],
'weights': ['uniform', 'distance']}
trained_knn = classification_trainer.knn(
scoring_metric='accuracy',
hyperparameter_grid=knn_hyperparameters,
randomized_search=True,
# Set this relative to the size of your hyperparameter space. Higher will train more models and be slower
# Lower will be faster and possibly less performant
number_iteration_samples=10
)
# ## Train a random forest classifier with a randomized search over custom hyperparameters
# TODO these are bogus hyperparams for random forest
random_forest_hyperparameters = {
'n_estimators': [50, 100, 200, 300],
'max_features': [1, 2, 3, 4],
'max_leaf_nodes': [None, 30, 400]}
trained_random_forest = classification_trainer.random_forest_classifier(
scoring_metric='accuracy',
hyperparameter_grid=random_forest_hyperparameters,
randomized_search=True,
# Set this relative to the size of your hyperparameter space. Higher will train more models and be slower
# Lower will be faster and possibly less performant
number_iteration_samples=10
)
# Show the random forest feature importance graph
hcai_tsm.plot_rf_features_from_tsm(
trained_random_forest,
classification_trainer.x_train,
feature_limit=20,
save=False)
# ## Train a custom ensemble of models
# The ensemble methods take a dictionary of TrainedSupervisedModels by a name of your choice
custom_ensemble = {
'KNN': classification_trainer.knn(
hyperparameter_grid=knn_hyperparameters,
randomized_search=False,
scoring_metric='roc_auc'),
'Logistic Regression': classification_trainer.logistic_regression(),
'Random Forest Classifier': classification_trainer.random_forest_classifier(
randomized_search=False,
scoring_metric='roc_auc')}
trained_ensemble = classification_trainer.ensemble_classification(
scoring_metric='roc_auc',
trained_model_by_name=custom_ensemble)
# Step 5: Evaluate and compare the models
# Create a list of all the models you just trained that you want to compare
models_to_compare = [trained_knn, trained_random_forest, trained_ensemble]
# Create a ROC plot that compares all the them.
hcai_tsm.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='ROC',
save=False)
# Create a PR plot that compares all the them.
hcai_tsm.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='PR',
save=False)
# Inspect the raw ROC or PR cutoffs
print(trained_random_forest.roc(print_output=False))
print(trained_random_forest.pr(print_output=False))
def main():
"""Template script for using healthcareai to train a classification model."""
# Load the included diabetes sample data
dataframe = healthcareai.load_diabetes()
# ...or load your own data from a .csv file: Uncomment to pull data from your CSV
# dataframe = healthcareai.load_csv('path/to/your.csv')
# ...or load data from a MSSQL server: Uncomment to pull data from MSSQL server
# server = 'localhost'
# database = 'SAM'
# query = """SELECT *
# FROM [SAM].[dbo].[DiabetesClincialSampleData]
# -- In this step, just grab rows that have a target
# WHERE ThirtyDayReadmitFLG is not null"""
#
# engine = hcai_db.build_mssql_engine_using_trusted_connections(server=server, database=database)
# dataframe = pd.read_sql(query, engine)
# Peek at the first 5 rows of data
print(dataframe.head(5))
# Drop columns that won't help machine learning
dataframe.drop(['PatientID'], axis=1, inplace=True)
# Step 1: Setup a healthcareai classification trainer. This prepares your data for model building
classification_trainer = healthcareai.SupervisedModelTrainer(
dataframe=dataframe,
predicted_column='ThirtyDayReadmitFLG',
model_type='classification',
grain_column='PatientEncounterID',
impute=True,
verbose=False)
# Look at the first few rows of your dataframe after loading the data
print('\n\n-------------------[ Cleaned Dataframe ]--------------------------')
print(classification_trainer.clean_dataframe.head())
# Step 2: train some models
# Train a KNN model
trained_knn = classification_trainer.knn()
# View the ROC and PR plots
trained_knn.roc_plot()
trained_knn.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_knn.roc()
# trained_knn.pr()
# Train a logistic regression model
trained_lr = classification_trainer.logistic_regression()
# View the ROC and PR plots
trained_lr.roc_plot()
trained_lr.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_lr.roc()
# trained_lr.pr()
# Train a random forest model and view the feature importance plot
trained_random_forest = classification_trainer.random_forest(save_plot=False)
# View the ROC and PR plots
trained_random_forest.roc_plot()
trained_random_forest.pr_plot()
# Uncomment if you want to see all the ROC and/or PR thresholds
# trained_random_forest.roc()
# trained_random_forest.pr()
# Create a list of all the models you just trained that you want to compare
models_to_compare = [trained_knn, trained_lr, trained_random_forest]
# Create a ROC plot that compares them.
tsm_plots.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='ROC',
save=False)
# Create a PR plot that compares them.
tsm_plots.tsm_classification_comparison_plots(
trained_supervised_models=models_to_compare,
plot_type='PR',
save=False)
# Once you are happy with the performance of any model, you can save it for use later in predicting new data.
# File names are timestamped and look like '2017-05-31T12-36-21_classification_RandomForestClassifier.pkl')
# Note the file you saved and that will be used in example_classification_2.py
trained_random_forest.save()