def bde(ctx):
delete_cached_model()
click.echo("Decision engine cache deleted")
delete_previous_analysis_reports()
click.echo("Analysis reports deleted")
get_decision_engine(get_ml_data())
click.echo("Decision engine created")
def dea(ctx):
delete_previous_analysis_reports()
click.echo("Analysis reports deleted")
ml_data = get_ml_data()
decision_engine = get_decision_engine(ml_data)
analyzer = DecisionEngineAnalyzer(decision_engine, ml_data)
analyzer.create_analysis_reports()
click.echo("Reports created in directory %s" % ANALYSIS_RESULTS_DIR)
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer
from data_processing.ml_data_prepairer import get_ml_data
from models.preprocess_pipeline import CongestiveHeartFailurePreprocessor
data = get_ml_data()
treatment_label_binarizer = LabelBinarizer()
preprocessor = CongestiveHeartFailurePreprocessor(False)
preprocessor.fit(data)
transformed_data = preprocessor.transform(data)
y = treatment_label_binarizer.fit_transform(data.treatment.values)
X_train, X_test, y_train, y_test = train_test_split(transformed_data, y, test_size=0.3)
pipeline = Pipeline([
('rf', RandomForestClassifier())
])
param_grid = [{
'rf__max_depth': list(range(9, 20)),
'rf__n_estimators': list(range(45, 70, 5)),
'rf__criterion': ["gini", "entropy"],
"rf__max_features": ["auto", None]
}]
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer
from data_processing.ml_data_prepairer import get_ml_data
from models.preprocess_pipeline import CongestiveHeartFailurePreprocessor
data = get_ml_data()
treatment_label_binarizer = LabelBinarizer()
preprocessor = CongestiveHeartFailurePreprocessor(False)
preprocessor.fit(data)
transformed_data = preprocessor.transform(data)
y = treatment_label_binarizer.fit_transform(data.treatment.values)
X_train, X_test, y_train, y_test = train_test_split(transformed_data,
y,
test_size=0.3)
pipeline = Pipeline([('rf', RandomForestClassifier())])
param_grid = [{
'rf__max_depth': list(range(9, 20)),
'rf__n_estimators': list(range(45, 70, 5)),
'rf__criterion': ["gini", "entropy"],
"rf__max_features": ["auto", None]
}]
def pd(ctx):
# When building a new dataset, we should clear all cache since the models and analysis are no longer valid
_all_clean()
get_ml_data()
click.echo("New dataset built")
import logging
from data_processing.ml_data_prepairer import get_ml_data
from models.build_decision_engine import get_decision_engine
from models.analysis.decision_engine_analyzer import DecisionEngineAnalyzer
logger = logging.getLogger()
logger.setLevel(logging.INFO)
congestive_heart_failure_data = get_ml_data()
decision_engine = get_decision_engine(congestive_heart_failure_data)
decision_engine_analyzer = DecisionEngineAnalyzer(decision_engine, congestive_heart_failure_data)
print("Important Features for outcome prediction")
print(decision_engine.get_outcome_feature_importance().sort_values('importance', ascending=False))
print("Important Features for actual treatment prediction")
print(decision_engine.get_actual_treatment_feature_importance().sort_values('importance', ascending=False))
recommended_treatment_overview = decision_engine_analyzer.get_recommended_treatment_overview()
print('Recommended treatment overview')
print(recommended_treatment_overview)
outcome_changes = decision_engine_analyzer.get_outcome_change_by_recommended_and_actual_treatment()
print('Recommended treatment counts per actual treatment')
print(outcome_changes)
top_treatment_improvements = outcome_changes[(outcome_changes.counts > 20) & (outcome_changes.survival_rate_improvement > 0.025)]
print("Top opportunities for treatment improvements")
import logging
from data_processing.ml_data_prepairer import get_ml_data
from models.build_decision_engine import get_decision_engine
from models.analysis.decision_engine_analyzer import DecisionEngineAnalyzer
logger = logging.getLogger()
logger.setLevel(logging.INFO)
congestive_heart_failure_data = get_ml_data()
decision_engine = get_decision_engine(congestive_heart_failure_data)
decision_engine_analyzer = DecisionEngineAnalyzer(
decision_engine, congestive_heart_failure_data)
print("Important Features for outcome prediction")
print(decision_engine.get_outcome_feature_importance().sort_values(
'importance', ascending=False))
print("Important Features for actual treatment prediction")
print(decision_engine.get_actual_treatment_feature_importance().sort_values(
'importance', ascending=False))
recommended_treatment_overview = decision_engine_analyzer.get_recommended_treatment_overview(
)
print('Recommended treatment overview')
print(recommended_treatment_overview)
outcome_changes = decision_engine_analyzer.get_outcome_change_by_recommended_and_actual_treatment(
)
