Refactoring

application/gui.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python3
-
 import sys
 import pathlib
 import PyQt5.QtGui

application/modeling.py

@@ -1,29 +1,19 @@
-import time
 import application.utils
-import flask
-import pandas as pd
+import application.modeling
 import dariah_topics
-import numpy as np
-import logging
 import pathlib
+import logging
 import lda
-import bokeh.plotting
-import bokeh.embed
-import werkzeug.utils
-import pathlib
 import time
-import sys
-import shutil
-import logging
-import tempfile
-import dariah_topics
 import flask
-import pandas as pd
+import shutil
 import numpy as np
+import pandas as pd
 import bokeh.plotting
 import bokeh.embed
 import werkzeug.utils
 
+
 # These messages are displayed during modeling:
 INFO_2A = "FYI: This might take a while..."
 INFO_3A = "In the meanwhile, have a look at"
@@ -48,9 +38,13 @@ def lda_modeling(document_term_arr, n_topics, n_iter, tempdir):
     return model
 
 
-def create_model(tempdir, bokeh_resources):
-    start = time.time()
+def workflow(tempdir, bokeh_resources):
+    """
+    Collects the user input, preprocesses the corpus, trains the LDA model,
+    creates visualizations, and dumps generated data.
+    """
     try:
+        start = time.time()
         user_input = {'files': flask.request.files.getlist('files'),
                       'num_topics': int(flask.request.form['num_topics']),
                       'num_iterations': int(flask.request.form['num_iterations'])}

application/utils.py

@@ -50,6 +50,24 @@ def decompress(filepath):
         return pickle.load(file)
 
 
+def load_data(tempdir):
+    """
+    Loads the generated data.
+    """
+    data_path = str(pathlib.Path(tempdir, 'data.pickle'))
+    parameter_path = str(pathlib.Path(tempdir, 'parameter.csv'))
+    topics_path = str(pathlib.Path(tempdir, 'topics.csv'))
+
+    data = application.utils.decompress(data_path)
+    parameter = pd.read_csv(parameter_path, index_col=0, encoding='utf-8')
+    parameter.columns = ['']  # remove column names
+    topics = pd.read_csv(topics_path, index_col=0, encoding='utf-8')
+
+    data['parameter'] = [parameter.to_html(classes='parameter', border=0)]
+    data['topics'] = [topics.to_html(classes='topics')]
+    return data
+
+
 def remove_markup(content):
     """
     Removes markup from text.
@@ -220,17 +238,3 @@ def is_connected(host='8.8.8.8', port=53, timeout=3):
         return True
     except:
         return False
-
-def load_data(TEMPDIR):
-    data_path = str(pathlib.Path(TEMPDIR, 'data.pickle'))
-    parameter_path = str(pathlib.Path(TEMPDIR, 'parameter.csv'))
-    topics_path = str(pathlib.Path(TEMPDIR, 'topics.csv'))
-
-    data = application.utils.decompress(data_path)
-    parameter = pd.read_csv(parameter_path, index_col=0, encoding='utf-8')
-    parameter.columns = ['']  # remove column names
-    topics = pd.read_csv(topics_path, index_col=0, encoding='utf-8')
-
-    data['parameter'] = [parameter.to_html(classes='parameter', border=0)]
-    data['topics'] = [topics.to_html(classes='topics')]
-    return data

application/web.py

@@ -42,7 +42,7 @@ def stream_template(template_name, **context):
         app.update_template_context(context)
         t = app.jinja_env.get_template(template_name)
         return t.stream(context)
-    stream = flask.stream_with_context(application.modeling.create_model(TEMPDIR, bokeh_resources))
+    stream = flask.stream_with_context(application.modeling.workflow(TEMPDIR, bokeh_resources))
     return flask.Response(stream_template('modeling.html', info=stream))