jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
mirror of https://github.com/Azure/MachineLearningNotebooks.git synced 2025-12-20 17:45:10 -05:00
Code Issues Projects Releases Wiki Activity

update samples from Release-129 as a part of SDK release

Browse Source
This commit is contained in:
amlrelsa-ms
2022-03-29 18:28:35 +00:00
parent ceaf82acc6
commit 08b0ba7854
537 changed files with 27112 additions and 151756 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
tutorials/compute-instance-quickstarts/quickstart-azureml-python-sdk/src/train.py
View File

@@ -1,72 +0,0 @@
import argparse
import os
import numpy as np
import glob
# import joblib
import mlflow
from sklearn.linear_model import LogisticRegression
from utils import load_data
# let user feed in 2 parameters, the dataset to mount or download,
# and the regularization rate of the logistic regression model
parser = argparse.ArgumentParser()
parser.add_argument(
"--data-folder", type=str, dest="data_folder", help="data folder mounting point"
)
parser.add_argument(
"--regularization", type=float, dest="reg", default=0.01, help="regularization rate"
)
args = parser.parse_args()
data_folder = args.data_folder
print("Data folder:", data_folder)
# load train and test set into numpy arrays
# note we scale the pixel intensity values to 0-1 (by dividing it with 255.0) so the model can converge faster.
X_train = (
load_data(
glob.glob(
os.path.join(data_folder, "**/train-images-idx3-ubyte.gz"), recursive=True
)[0],
False,
) / 255.0
)
X_test = (
load_data(
glob.glob(
os.path.join(data_folder, "**/t10k-images-idx3-ubyte.gz"), recursive=True
)[0],
False,
) / 255.0
)
y_train = load_data(
glob.glob(
os.path.join(data_folder, "**/train-labels-idx1-ubyte.gz"), recursive=True
)[0],
True,
).reshape(-1)
y_test = load_data(
glob.glob(
os.path.join(data_folder, "**/t10k-labels-idx1-ubyte.gz"), recursive=True
)[0],
True,
).reshape(-1)
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape, sep="\n")
# use mlflow autologging
mlflow.autolog()
print("Train a logistic regression model with regularization rate of", args.reg)
clf = LogisticRegression(
C=1.0 / args.reg, solver="liblinear", multi_class="auto", random_state=42
)
clf.fit(X_train, y_train)
print("Predict the test set")
y_hat = clf.predict(X_test)
# calculate accuracy on the prediction
acc = np.average(y_hat == y_test)
print("Accuracy is", acc)