def setUp(self):
name = "logistic-test"
author = "srinidhi"
description = "income-level logistic regression"
syncer_obj = SyncerTest(
NewOrExistingProject(name, author, description),
DefaultExperiment(), NewExperimentRun("Abc"),
ThriftConfig(None, None))
# Creating the pipeline
pca = decomposition.PCA()
lr = linear_model.LinearRegression()
pipe = Pipeline(steps=[('pca', pca), ('logistic', lr)])
model = linear_model.LinearRegression()
np.random.seed(0)
X = pd.DataFrame(np.random.randint(0, 100, size=(100, 2)),
columns=list('AB'))
y = pd.DataFrame(np.random.randint(0, 100, size=(100, 1)),
columns=['output'])
# Add tags for models / dataframes
syncer_obj.add_tag(X, "digits-dataset")
syncer_obj.add_tag(pipe, "pipeline with pca + logistic")
syncer_obj.add_tag(pca, "decomposition PCA")
syncer_obj.add_tag(lr, "basic linear reg")
syncer_obj.clear_buffer()
pipe.fit_sync(X, y)
events = syncer_obj.sync()
self.pipeline_event = events[0]
def run_pipeline_anova_workflow():
name = "pipeline scikit example"
author = "srinidhi"
description = "anova filter pipeline"
syncer_obj = Syncer(
NewOrExistingProject(name, author, description),
DefaultExperiment(),
NewExperimentRun("Abc"))
# import some data to play with
X, y = samples_generator.make_classification(
n_informative=5, n_redundant=0, random_state=42)
x_train, x_test, y_train, y_test = cross_validation.train_test_split_sync(
X, y, test_size=0.3, random_state=0)
syncer_obj.add_tag(X, "samples generated data")
syncer_obj.add_tag(x_train, "training data")
syncer_obj.add_tag(x_test, "testing data")
# ANOVA SVM-C
# 1) anova filter, take 5 best ranked features
anova_filter = SelectKBest(f_regression, k=5)
syncer_obj.add_tag(anova_filter, "Anova filter, with k=5")
# 2) svm
clf = svm.SVC(kernel='linear')
syncer_obj.add_tag(clf, "SVC with linear kernel")
anova_svm = Pipeline([('anova', anova_filter), ('svc', clf)])
syncer_obj.add_tag(anova_svm, "Pipeline with anova_filter and SVC")
# Fit the pipeline on the training set
anova_svm.fit_sync(x_train, y_train)
y_pred = anova_svm.predict(x_test)
# Compute metrics for the model on the testing set
f1 = SyncableMetrics.compute_metrics(
anova_svm, f1_score, y_test, y_pred, x_test, "predictionCol",
'label_col')
precision = SyncableMetrics.compute_metrics(
anova_svm, precision_score, y_test, y_pred, x_test, "predictionCol",
'label_col')
syncer_obj.sync()
return syncer_obj, f1, precision, x_train, x_test
new_df[colname + "_index"] = transformed_vals
else:
new_df[colname] = df[colname]
# Creating the pipeline
pca = decomposition.PCA()
lr = linear_model.LogisticRegression()
pipe = Pipeline(steps=[('pca', pca), ('logistic', lr)])
# Separating dataset into training and testing sets
x_train, x_test, y_train, y_test = cross_validation.train_test_split_sync(
new_df, new_df['income_level'], test_size=0.3, random_state=0)
# We don't want to include our label (income_level) when fitting
partial_training = x_train[x_train.columns[:-1]]
partial_testing = x_test[x_test.columns[:-1]]
# Fit the pipeline
pipe.fit_sync(partial_training, y_train)
y_pred = pipe.predict(partial_testing)
# Compute various metrics on the testing set
SyncableMetrics.compute_metrics(
pipe, f1_score, y_test, y_pred, partial_testing, "predictionCol",
'income_level')
SyncableMetrics.compute_metrics(
pipe, precision_score, y_test, y_pred, partial_testing, "predictionCol",
'income_level')
syncer_obj.sync()
