From 566f04ad56c3be0ec364744cc93413a7e8518448 Mon Sep 17 00:00:00 2001
From: alvinzhou66 <43176447+alvinzhou66@users.noreply.github.com>
Date: Wed, 11 Nov 2020 20:17:24 -0800
Subject: [PATCH] v2.4

---
 Docker_workspace/Dockerfile                  | 18 ++++++++++++++++++
 README.md                                    |  2 +-
 binary_classifier/SOMEF_BIN_classifier.ipynb |  4 ++++
 3 files changed, 23 insertions(+), 1 deletion(-)
 create mode 100644 Docker_workspace/Dockerfile

diff --git a/Docker_workspace/Dockerfile b/Docker_workspace/Dockerfile
new file mode 100644
index 0000000..1516f5d
--- /dev/null
+++ b/Docker_workspace/Dockerfile
@@ -0,0 +1,18 @@
+FROM continuumio/miniconda3
+
+RUN apt-get update && apt-get install -y \
+  gcc
+
+RUN git clone https://github.com/alvinzhou66/classification-of-scientific-software
+
+RUN conda install -c conda-forge yarn
+
+RUN cd classification-of-scientific-software && yarn install
+
+RUN pip install --upgrade pip
+
+COPY requirements.txt /opt/app/requirements.txt
+
+RUN pip install -r /opt/app/requirements.txt
+
+WORKDIR classification-of-scientific-software
diff --git a/README.md b/README.md
index d36be22..e47aacb 100644
--- a/README.md
+++ b/README.md
@@ -31,7 +31,7 @@ pip install -r requirements.txt
 ```
 3. Docker.  
 Install Docker first.
-In the directory which has <i>our Dockerfile</i>, build the docker container:
+In the directory which has <i>our Dockerfile (in folder -> /Docker_workspace)</i>, build the docker container:
 ```
 docker build -t coss .
 ```
diff --git a/binary_classifier/SOMEF_BIN_classifier.ipynb b/binary_classifier/SOMEF_BIN_classifier.ipynb
index a6136be..c12a36a 100644
--- a/binary_classifier/SOMEF_BIN_classifier.ipynb
+++ b/binary_classifier/SOMEF_BIN_classifier.ipynb
@@ -10,6 +10,10 @@
     "import torch \n",
     "from DNN import FFN\n",
     "import re\n",
+    "import nltk\n",
+    "nltk.download('punkt')\n",
+    "nltk.download('treebank')\n",
+    "nltk.download('stopwords')\n",
     "from nltk.tokenize import word_tokenize\n",
     "from nltk.corpus import stopwords\n",
     "import pandas as pd\n",