Merge branch 'master' into Installation-Documentation-#57

.github/workflows/main.yml

@@ -9,19 +9,20 @@ jobs:
     strategy:
       matrix:
         os: [Ubuntu, MacOS]
-        python-version: [3.6, 3.7, 3.8]
+        python-version: [3.7, 3.8]
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2
+      id: setup-python
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install Pipenv
-      run: |
-        pip install pipenv --upgrade
+    - name: Setup Pipenv
+      uses: dschep/install-pipenv-action@v1
     - name: Install dependencies
       run: |
-        pipenv install --dev --skip-lock
+        # install dependencies according to the lock file
+        pipenv install --dev --ignore-pipfile --python ${{ steps.setup-python.outputs.python-version }}
         pipenv run python -m spacy download en_core_web_sm
     - name: Run test with pytest
       run: |

CONTRIBUTING.md

@@ -51,7 +51,7 @@ code contribution.
 ### Development Environment
 
 In order to contribute code or documentation to the project, the project
-maintainers suggest installing the release of Python versions above 3.6. You can
+maintainers suggest installing the release of Python versions above 3.7. You can
 learn more about installing and managing python versions with `pyenv` from
 [here](https://realpython.com/intro-to-pyenv/). In addition to installing `Git` to
 access the project's GitHub repository, you should also install `Pipenv` for its
@@ -108,9 +108,9 @@ pipenv run streamlit run streamlit_web.py
 #### Develop GatorMiner on Windows
 
 GatorMiner depends on gensim, and gensim requires Microsoft Visual C++ 14.0+. You can check the version you have from
-`Control Panel -> Programs and Features`. To download or update this, go to the 
-[Visual Studio 2019 Downloads](https://visualstudio.microsoft.com/downloads/), scroll down and 
-expand the `Tools for Visual Studio 2019` and click the download link for `Build tools for Visual Studio 2019`. 
+`Control Panel -> Programs and Features`. To download or update this, go to the
+[Visual Studio 2019 Downloads](https://visualstudio.microsoft.com/downloads/), scroll down and
+expand the `Tools for Visual Studio 2019` and click the download link for `Build tools for Visual Studio 2019`.
 
 Once the installer is downloaded, launch it and select the `C++ build tools` option under `Desktop and Mobile`.
 After that select install at the bottom and wait.
@@ -120,7 +120,7 @@ installing, the installer will ask to restart the computer to finish the install
 After your computer has finished installing the C++ build tools, you may need to reinstall the dependencies. To do this,
 just run the `pipenv install --dev` command as previously instructed.
 
-If you still receive the error, delete the `Pipfile.lock` file in the root of the GatorMiner directory and reinstall 
+If you still receive the error, delete the `Pipfile.lock` file in the root of the GatorMiner directory and reinstall
 using the previous command.
 
 #### Test GatorMiner with Sample Data

Pipfile

@@ -11,7 +11,7 @@ pytest-cov = "*"
 
 [packages]
 matplotlib = "*"
-gensim = '*'
+gensim = "~=3.8.3"
 spacy = "~=2.3"
 sklearn = "*"
 pytest = "*"
@@ -23,6 +23,7 @@ altair = "*"
 textblob = "*"
 scipy = "*"
 pylint = "*"
+importlib-metadata = "*"
 
 [pipenv]
 allow_prereleases = true

README.md

@@ -84,7 +84,7 @@ Network URL: http://xxx.xxx.x.x:8501
 
 The web interface will be automatically opened in your browser:
 
-![browser](resources/images/landing_page.png)
+<img src="resources/images/landing_page.png" alt="browser" style="width:100%"/>
 
 ### Data Retreiving
 
@@ -124,7 +124,7 @@ with GatorGrader [here](https://github.com/enpuyou/script-api-lambda-dynamodb).
 Once the documents are successfully imported, you can then navigate through
 the select box in the sidebar to view the text analysis:
 
-![select box](resources/images/select_box.png)
+<img src="resources/images/select_box.png" alt="select box" style="width:100%"/>
 
 ##### Reflection Documents
 
@@ -143,10 +143,10 @@ format of json reports GatorMiner gathers from AWS.
 
 ### Analysis
 
-![frequency](resources/images/frequency.png)
-![sentiment](resources/images/sentiment.png)
-![similarity](resources/images/similarity.png)
-![topic](resources/images/topic.png)
+<img src="resources/images/frequency.png" alt="frequency" style="width:100%"/>
+<img src="resources/images/sentiment.png" alt="sentiment" style="width:100%"/>
+<img src="resources/images/similarity.png" alt="similarity" style="width:100%"/>
+<img src="resources/images/topic.png" alt="topic" style="width:100%"/>
 
 ### Contribution
 

src/summarizer.py

@@ -1,7 +1,7 @@
 """Text summary"""
 import logging
 from typing import Dict, List
-from gensim.summarization import summarize
+from gensim.summarization.summarizer import summarize
 from . import markdown as md
 
 # pylint: disable=logging-fstring-interpolation

streamlit_web.py

@@ -2,7 +2,9 @@
 
 import re
 
+import base64
 import numpy as np
+import os
 import pandas as pd
 from sklearn.manifold import TSNE
 import spacy
@@ -60,8 +62,7 @@ def main():
         if debug_mode:
             st.write(main_df)
         if analysis_mode == "Home":
-            with open("README.md") as readme_file:
-                st.markdown(readme_file.read())
+            readme()
         else:
             if analysis_mode == "Frequency Analysis":
                 st.title(analysis_mode)
@@ -83,13 +84,26 @@ def main():
                 interactive()
             success_msg.empty()
 
+def readme():
+    """function to load and configurate readme source"""
+
+    with open("README.md") as readme_file:
+        readme_src = readme_file.read()
+        for file in os.listdir("resources/images"):
+            if file.endswith(".png"):
+                img_path = f"resources/images/{file}"
+                with open(img_path, "rb") as f:
+                    img_bin = base64.b64encode(f.read()).decode()
+                readme_src = readme_src.replace(img_path, f"data:image/png;base64,{img_bin}")
+
+        st.markdown(readme_src, unsafe_allow_html=True)
 
 def landing_pg():
     """landing page"""
     landing = st.sidebar.selectbox("Welcome", ["Home", "Interactive"])
+
     if landing == "Home":
-        with open("README.md") as readme_file:
-            st.markdown(readme_file.read())
+        readme()
     else:
         interactive()
 
@@ -120,8 +134,7 @@ def retreive_data(data_retreive):
         except TypeError:
             st.sidebar.warning(
                 "No data imported. Please check the reflection document input")
-            with open("README.md") as readme_file:
-                st.markdown(readme_file.read())
+            readme()
         else:
             global success_msg
             success_msg = None
@@ -157,8 +170,7 @@ def import_data(data_retreive_method, paths):
                 json_lst.append(md.collect_md(path))
         except FileNotFoundError as err:
             st.sidebar.text(err)
-            with open("README.md") as readme_file:
-                st.markdown(readme_file.read())
+            readme()
     else:
         passbuild = st.sidebar.checkbox(
             "Only retreive build success records", value=True)
@@ -169,8 +181,7 @@ def import_data(data_retreive_method, paths):
                 json_lst.append(ju.clean_report(response))
         except (EnvironmentError, Exception) as err:
             st.sidebar.error(err)
-            with open("README.md") as readme_file:
-                st.markdown(readme_file.read())
+            readme()
     # when data is retreived
     if json_lst:
         raw_df = pd.DataFrame()

tests/test_markdown.py

@@ -22,7 +22,8 @@ def test_get_file_names(tmp_path):
     para_2.write_text("text")
     output = md.get_file_names(directory)
     expected = [f"{directory}/hello.md", f"{directory}/world.md"]
-    assert expected == output
+    assert expected[0] in output
+    assert expected[1] in output
 
 
 def test_md_parser():