Add pandas-profiling report

Makefile

@@ -4,6 +4,7 @@ out: all-data
 	python massage_templates.py
 	python copy_massaged_data.py
 	python generate_charts.py
+	python generate_profiling.py
 	cp data/results.xlsx out/raw.xlsx
 	cp data/results.tsv out/raw.tsv
 

generate_profiling.py

@@ -0,0 +1,12 @@
+from data_ingest import read_data
+from pandas_profiling import ProfileReport
+
+
+def main():
+    df = read_data()
+    profile = ProfileReport(df)
+    profile.to_file("out/profiling_report.html")
+
+
+if __name__ == "__main__":
+    main()

requirements.in

@@ -2,3 +2,4 @@ bokeh
 jinja2
 openpyxl
 pandas
+https://github.com/akx/pandas-profiling/archive/no-hard-ipywidgets.zip#egg=pandas-profiling

requirements.txt

@@ -4,43 +4,127 @@
 #
 #    pip-compile requirements.in
 #
+attrs==20.3.0
+    # via
+    #   pandas-profiling
+    #   visions
 bokeh==2.2.3
     # via -r requirements.in
+certifi==2020.12.5
+    # via requests
+chardet==4.0.0
+    # via requests
+confuse==1.4.0
+    # via pandas-profiling
+cycler==0.10.0
+    # via matplotlib
+decorator==4.4.2
+    # via networkx
 et-xmlfile==1.0.1
     # via openpyxl
+htmlmin==0.1.12
+    # via pandas-profiling
+idna==2.10
+    # via requests
+imagehash==4.2.0
+    # via visions
 jdcal==1.4.1
     # via openpyxl
 jinja2==2.11.3
     # via
     #   -r requirements.in
     #   bokeh
+    #   pandas-profiling
+joblib==1.0.1
+    # via pandas-profiling
+kiwisolver==1.3.1
+    # via matplotlib
 markupsafe==1.1.1
     # via jinja2
+matplotlib==3.3.4
+    # via
+    #   missingno
+    #   pandas-profiling
+    #   seaborn
+missingno==0.4.2
+    # via pandas-profiling
+networkx==2.5
+    # via visions
 numpy==1.20.1
     # via
     #   bokeh
+    #   imagehash
+    #   matplotlib
+    #   missingno
     #   pandas
+    #   pandas-profiling
+    #   pywavelets
+    #   scipy
+    #   seaborn
+    #   visions
 openpyxl==3.0.6
     # via -r requirements.in
 packaging==20.9
     # via bokeh
-pandas==1.2.2
+https://github.com/akx/pandas-profiling/archive/no-hard-ipywidgets.zip#egg=pandas-profiling
     # via -r requirements.in
+pandas==1.2.2
+    # via
+    #   -r requirements.in
+    #   pandas-profiling
+    #   seaborn
+    #   visions
 pillow==8.1.0
-    # via bokeh
+    # via
+    #   bokeh
+    #   imagehash
+    #   matplotlib
+    #   visions
 pyparsing==2.4.7
-    # via packaging
+    # via
+    #   matplotlib
+    #   packaging
 python-dateutil==2.8.1
     # via
     #   bokeh
+    #   matplotlib
     #   pandas
 pytz==2021.1
     # via pandas
+pywavelets==1.1.1
+    # via imagehash
 pyyaml==5.4.1
-    # via bokeh
+    # via
+    #   bokeh
+    #   confuse
+requests==2.25.1
+    # via pandas-profiling
+scipy==1.6.1
+    # via
+    #   imagehash
+    #   missingno
+    #   pandas-profiling
+    #   seaborn
+seaborn==0.11.1
+    # via
+    #   missingno
+    #   pandas-profiling
 six==1.15.0
-    # via python-dateutil
+    # via
+    #   cycler
+    #   imagehash
+    #   python-dateutil
+tangled-up-in-unicode==0.0.6
+    # via
+    #   pandas-profiling
+    #   visions
 tornado==6.1
     # via bokeh
+tqdm==4.57.0
+    # via pandas-profiling
 typing-extensions==3.7.4.3
     # via bokeh
+urllib3==1.26.3
+    # via requests
+visions[type_image_path]==0.6.0
+    # via pandas-profiling

template/index.html

@@ -29,6 +29,7 @@
     <li><a href="data.html">Lähdedata (HTML)</a></li>
     <li><a href="data.json">Lähdedata (JSON)</a></li>
     <li><a href="data.xlsx">Lähdedata (XLSX)</a></li>
+    <li><a href="profiling_report.html">Lähdedatan analyysi</a></li>
     <li><a href="raw.tsv">Raakadata (TSV)</a></li>
     <li><a href="raw.xlsx">Raakadata (XLSX)</a></li>
 </ul>