Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Small update #12

Open
wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Small update #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
228f585
Small update to Project.ipynb for the first part of the tutorial
May 5, 2020
8ee5a1d
Start on pytorch
May 5, 2020
7b2568f
Add endpoint and and update html
May 7, 2020
884bf75
Merge pull request #1 from benjaminlees/update/Project.ipynb
benjaminlees May 7, 2020
2e851eb
Update a unfilled question
May 7, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ __pycache__/
# Distribution / packaging
.Python
env/
data/
cache/
build/
develop-eggs/
dist/
Expand Down Expand Up @@ -105,4 +107,4 @@ ENV/

# Notebook files
Sentiment Analysis/aclImdb_v1.tar.gz
Sentiment Analysis/aclImdb/
Sentiment Analysis/aclImdb/
79 changes: 69 additions & 10 deletions Mini-Projects/IMDB Sentiment Analysis - XGBoost (Updating a Model) - Solution.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,19 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -433,9 +447,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "NameError",
"evalue": "name 'os' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-2-2738a4cc0740>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0mprefix\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'sentiment-update'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m \u001b[0mtest_location\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msession\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupload_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'test.csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey_prefix\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprefix\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 9\u001b[0m \u001b[0mval_location\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msession\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupload_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'validation.csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey_prefix\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprefix\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[0mtrain_location\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msession\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupload_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'train.csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey_prefix\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprefix\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mNameError\u001b[0m: name 'os' is not defined"
]
}
],
"source": [
"import sagemaker\n",
"\n",
Expand Down Expand Up @@ -470,7 +496,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -483,9 +509,18 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING:root:There is a more up to date SageMaker XGBoost image. To use the newer image, please set 'repo_version'='0.90-1'. For example:\n",
"\tget_image_uri(region, 'xgboost', '0.90-1').\n"
]
}
],
"source": [
"# We need to retrieve the location of the container which is provided by Amazon for using XGBoost.\n",
"# As a matter of convenience, the training and inference code both use the same container.\n",
Expand All @@ -496,7 +531,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -531,9 +566,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "NameError",
"evalue": "name 'train_location' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-6-44fb05642cfc>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0ms3_input_train\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msagemaker\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0ms3_input\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms3_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrain_location\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontent_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0ms3_input_validation\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msagemaker\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0ms3_input\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms3_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mval_location\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontent_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mNameError\u001b[0m: name 'train_location' is not defined"
]
}
],
"source": [
"s3_input_train = sagemaker.s3_input(s3_data=train_location, content_type='csv')\n",
"s3_input_validation = sagemaker.s3_input(s3_data=val_location, content_type='csv')"
Expand Down Expand Up @@ -561,9 +608,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "NameError",
"evalue": "name 'xgb' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-1-6b6b431e93bb>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mxgb_transformer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mxgb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransformer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minstance_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minstance_type\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'ml.m4.xlarge'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mNameError\u001b[0m: name 'xgb' is not defined"
]
}
],
"source": [
"xgb_transformer = xgb.transformer(instance_count = 1, instance_type = 'ml.m4.xlarge')"
]
Expand Down
Loading