def main():
# Add arguments to script
parser = argparse.ArgumentParser()
parser.add_argument(
"--C",
type=float,
default=1.0,
help=
"Inverse of regularization strength. Smaller values cause stronger regularization",
)
parser.add_argument(
"--max_iter",
type=int,
default=100,
help="Maximum number of iterations to converge",
)
args = parser.parse_args()
run.log("Regularization Strength:", np.float(args.C))
run.log("Max iterations:", np.int(args.max_iter))
ds = TabularDatasetFactory().from_delimited_files(
path=
"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
)
x, y = clean_data(ds)
# Split data into train and test sets.
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.33,
random_state=7)
model = LogisticRegression(C=args.C,
max_iter=args.max_iter).fit(x_train, y_train)
accuracy = model.score(x_test, y_test)
run.log("Accuracy", np.float(accuracy))
pred_prob = model.predict_proba(x_test)
auc_score = roc_auc_score(y_test, pred_prob[:, 1], average="weighted")
run.log("AUC", np.float(auc_score))
# files saved in the "outputs" folder are automatically uploaded into run history
os.makedirs("outputs", exist_ok=True)
joblib.dump(model, "./outputs/model.joblib")
def main():
# Add arguments to src
parser = argparse.ArgumentParser()
parser.add_argument(
'--C',
type=float,
default=1.0,
help=
"Inverse of regularization strength. Smaller values cause stronger regularization"
)
parser.add_argument('--max_iter',
type=int,
default=100,
help="Maximum number of iterations to converge")
args = parser.parse_args()
run.log("Regularization Strength:", np.float(args.C))
run.log("Max iterations:", np.int(args.max_iter))
path = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
factory = TabularDatasetFactory()
ds = factory.from_delimited_files(path)
X, y = clean_data(ds)
# Split data into train and test sets.
train_data, test_data, train_label, test_label = train_test_split(
X, y, test_size=0.3, random_state=42)
model = LogisticRegression(C=args.C, max_iter=args.max_iter).fit(
train_data, train_label)
accuracy = model.score(test_data, test_label)
run.log("Accuracy", np.float(accuracy))
os.makedirs('outputs', exist_ok=True)
# Save model
joblib.dump(model, 'outputs/model.joblib')
def main():
# Add arguments to script
parser = argparse.ArgumentParser()
parser.add_argument('--C', type=float, default=1.0, help="Inverse of regularization strength. Smaller values cause stronger regularization")
parser.add_argument('--max_iter', type=int, default=100, help="Maximum number of iterations to converge")
args = parser.parse_args()
run.log("Regularization Strength:", np.float(args.C))
run.log("Max iterations:", np.int(args.max_iter))
# TODO: Create TabularDataset using TabularDatasetFactory
# Data is located at:
# "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
### YOUR CODE HERE ###
## Added code to inport TabularDataset using TabularDatasetFactory Class
factory = TabularDatasetFactory()
train_data_path = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
ds = factory.from_delimited_files(path=train_data_path)
# Clean the data
x, y = clean_data(ds)
# TODO: Split data into train and test sets.
### YOUR CODE HERE ###
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
# Fit model using Logistic Regression with inpur arguments C -> regularization strength
# Importance of Regularization in Logistic regression:
# https://stackoverflow.com/questions/22851316/what-is-the-inverse-of-regularization-strength-in-logistic-regression-how-shoul
# https://www.coursera.org/lecture/machine-learning/regularized-logistic-regression-4BHEy
model = LogisticRegression(C=args.C, max_iter=args.max_iter).fit(x_train, y_train)
# Download best model using the joblib library
os.makedirs('outputs', exist_ok=True)
joblib.dump(model, 'outputs/model.joblib')
accuracy = model.score(x_test, y_test)
run.log("Accuracy", np.float(accuracy))
def main():
# Add arguments to script
parser = argparse.ArgumentParser()
parser.add_argument(
'--C',
type=float,
default=1.0,
help=
"Inverse of regularization strength. Smaller values cause stronger regularization"
)
parser.add_argument('--max_iter',
type=int,
default=100,
help="Maximum number of iterations to converge")
args = parser.parse_args()
run.log("Regularization Strength:", np.float(args.C))
run.log("Max iterations:", np.int(args.max_iter))
factory = TabularDatasetFactory()
train_data_path = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
valid_data_path = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_validate.csv"
train_ds = factory.from_delimited_files(train_data_path)
valid_ds = factory.from_delimited_files(valid_data_path)
X_train, y_train = clean_data(train_ds)
X_valid, y_valid = clean_data(valid_ds)
model = LogisticRegression(C=args.C,
max_iter=args.max_iter).fit(X_train, y_train)
accuracy = model.score(X_valid, y_valid)
run.log("Accuracy", np.float(accuracy))
os.makedirs('outputs', exist_ok=True)
joblib.dump(model, 'outputs/bankmarketing-logit-model.joblib')
def main():
# Add arguments to script
parser = argparse.ArgumentParser()
parser.add_argument('--learning_rate',
type=float,
default=0.03,
help="Learning rate param for lgbm")
parser.add_argument('--max_depth',
type=int,
default=10,
help="Limit the tree depth explicitly")
parser.add_argument('--num_leaves',
type=int,
default=255,
help="Control the complexity of the tree model")
parser.add_argument('--min_data_in_leaf',
type=int,
default=3,
help="Large value can avoid growing too deep a tree")
parser.add_argument('--num_iterations',
type=int,
default=500,
help="Number of boosting iterations")
args = parser.parse_args()
run.log("learning-rate:", np.float(args.learning_rate))
run.log("max_depth:", np.int(args.max_depth))
run.log("num_leaves", np.int(args.num_leaves))
run.log("min_data_in_leaf", np.int(args.min_data_in_leaf))
run.log("num_iterations", np.int(args.num_iterations))
factory = TabularDatasetFactory()
train_data_path = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
valid_data_path = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_validate.csv"
train_ds = factory.from_delimited_files(train_data_path)
valid_ds = factory.from_delimited_files(valid_data_path)
X_train, y_train = clean_data(train_ds)
X_valid, y_valid = clean_data(valid_ds)
d_train = lgbm.Dataset(X_train, label=y_train)
lgbm_params = {}
lgbm_params['learning_rate'] = args.learning_rate
lgbm_params['boosting_type'] = 'gbdt'
lgbm_params['objective'] = 'binary'
lgbm_params['metric'] = 'binary_logloss'
lgbm_params['max_depth'] = args.max_depth
lgbm_params['num_leaves'] = args.num_leaves
lgbm_params['min_data_in_leaf'] = args.min_data_in_leaf
lgbm_params['colsample_bytree'] = 1.0,
model = lgbm.train(lgbm_params, d_train, args.num_iterations)
accuracy = accuracy_score(
model.predict(X_valid).round(0).astype(int), y_valid)
run.log("Accuracy", np.float(accuracy))
os.makedirs('outputs', exist_ok=True)
joblib.dump(model, 'outputs/bankmarketing-lgbm-model.joblib')
import os
import numpy as np
from sklearn.metrics import mean_squared_error
import joblib
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
import pandas as pd
from azureml.core.run import Run
from azureml.data.dataset_factory import TabularDatasetFactory
# TODO: Create TabularDataset using TabularDatasetFactory
# Data is located at:
# "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv"
### YOUR CODE HERE ###
ds = TabularDatasetFactory() \
.from_delimited_files("https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv")
def clean_data(data):
# Dict for cleaning data
months = {
"jan": 1,
"feb": 2,
"mar": 3,
"apr": 4,
"may": 5,
"jun": 6,
"jul": 7,
"aug": 8,
"sep": 9,
"oct": 10,
