Sc 107/default extention file selection

What's new:

• Automatically goes to the correct dir, depending if you look for shadows or source files!
• Has .csv as default instead of .txt
• Added .TextGrid as option
• Title of file selection window dependent on whether you look for source or shadow files
• File selection function has no code duplication anymore
• Layout of code in some other files is fixed to meet PEP standards

mvc/model.py

@@ -20,16 +20,18 @@ class ModelClass:
 
         # Data(structures)
         self.file_path_source = {}  # Dictionary of source files
-        self.file_path_shadow = {}  # Participant objects, containing their shadow files
-        self.data_source = None  # internal representation of file_path_source (pandas df)
-        self.data_shadow = None  # internal representation of file_path_shadow (pandas df)
-        self.analysis_results = None # tuple of the results following analysis
+        # Participant objects, containing their shadow files
+        self.file_path_shadow = {}
+        # internal representation of file_path_source (pandas df)
+        self.data_source = None
+        # internal representation of file_path_shadow (pandas df)
+        self.data_shadow = None
+        self.analysis_results = None  # tuple of the results following analysis
         self.save_pref = "standard"  # Possible codes: 'standard' and 'perpart'
 
     def read_file(self):
         """Reads the .txt or .csv and starts their analysis."""
 
-
         # When selecting CSVs, run comparison stuff so far:
         for p_num in self.file_path_shadow:
             shadow_files = self.file_path_shadow[p_num].get_shadow_files()
@@ -37,29 +39,30 @@ class ModelClass:
                 print(sh_file_key)
                 shadow_file_path = shadow_files[sh_file_key]
                 print(self.file_path_source.keys())
-                source_file_path = self.file_path_source[sh_file_key[2:]]#Note the 2: is a bit crude. But needed for now
+                # Note the 2: is a bit crude. But needed for now
+                source_file_path = self.file_path_source[sh_file_key[2:]]
                 if ".txt" in shadow_file_path:
-                    self.read_txt(source_file_path,shadow_file_path,p_num)
+                    self.read_txt(source_file_path, shadow_file_path, p_num)
                 elif ".csv" in shadow_file_path:
                     reader = CSVReader(source_file_path, shadow_file_path)
                     source_words, shadow_words = reader.read()
-                    #print(source_words,shadow_words)
+                    # print(source_words,shadow_words)
                     self.stats.words_source = source_words
                     self.stats.words_shadow = shadow_words
                     comparer = DataComparer(source_words, shadow_words)
                     comparer.start()
-                    #self.stats.analyze()
+                    # self.stats.analyze()
         # User preferences/settings
         self.save_pref = "standard"  # Possible codes: 'standard' & 'perpart'
 
-    def read_txt(self,source_file_path,shadow_file_path):
+    def read_txt(self, source_file_path, shadow_file_path):
         """
         Interprets the stored input files and stores their contents in pandas
         dataframes.
         The dataframes have columns 'tekst', 'Start', 'End' and 'comment'.
         Their rows are indexed with an integer.
 
-        Extension: When multiple source & shadow files used, assume equal amount.
+        Extension: When multiple source/shadow files used, assume equal amount.
                    So one on one matching needs to be in place.
         """
         # To test when file_path_source and file_path_shadow are not available,
@@ -70,10 +73,10 @@ class ModelClass:
         analyses_results = {}
 
         with open(source_file_path, 'r') as source,\
-            open(shadow_file_path, 'r') as shadow:
-                self.stats.data_source = self.format_input(source)
-                self.stats.data_shadow = self.format_input(shadow)
-                analyses_results[p_num] = self.stats.analyze()
+             open(shadow_file_path, 'r') as shadow:
+                 self.stats.data_source = self.format_input(source)
+                 self.stats.data_shadow = self.format_input(shadow)
+                 analyses_results[p_num] = self.stats.analyze()
 
         self.analysis_results = analyses_results
 
@@ -110,7 +113,7 @@ class ModelClass:
             output.append(ms + 1000 * (seconds + 60 * (minutes + 60 * hours)))
         return output
 
-    def save_txt(self, save_path):  # Needs to be extended to save multiple files
+    def save_txt(self, save_path):  # Has to be extended to save multiple files
         """ Function to save a file given the file_name
         Furthermore, it can convert times to hour format if deemed necessary.
 
@@ -128,18 +131,20 @@ class ModelClass:
             total_latency, avg_latency, latency_p_word = latency_results
             mistakes_result = part_results[1]
 
-            # Make a new frame and copy the elements so that data is not changed:
+            # Make a new frame & copy the elements so that data is not changed:
             output_latencies = pd.DataFrame(np.zeros(latency_p_word.shape),
                                             columns=["tekst", "latency"])
             output_latencies["latency"] = [self.stats.to_hour_format(latency)
-                                           for latency in latency_p_word["latency"]]
+                                           for latency in latency_p_word[
+                                               "latency"]]
             output_latencies["tekst"] = latency_p_word["tekst"]
 
             # Add comparison number when multiple files are used and put in map
             txt_path = save_path
             csv_path = save_path[:-4] + "_csv.txt"
             if len(self.analysis_results) > 1:
-                # Implements a map structure per participant. If this option is selected.
+                # Implements a map structure per participant.
+                # If this option is selected.
                 if self.save_pref == "perpart":
                     folder_path_part = save_path[:-4] + "/" + part_num
                     os.mkdir(folder_path_part)
@@ -153,8 +158,8 @@ class ModelClass:
             output_latencies.to_csv(csv_path, index=False)
             np.savetxt(txt_path, output_latencies, fmt='%s',
                        header="tekst, latency",
-                       footer="total latency: {}ms, average latency: {}ms, pairwise "
-                              "mistakes: {}"
+                       footer="total latency: {}ms, average latency: {}ms,"
+                              "pairwise mistakes: {}"
                        .format(total_latency, avg_latency, mistakes_result),
                        comments="", delimiter=' ')
 
@@ -184,6 +189,8 @@ class ModelClass:
         else:
             participant_name = name.split('_')[0]
             if participant_name in self.file_path_shadow.keys():
-                self.file_path_shadow[participant_name].add_shadow_file(file_path)
+                self.file_path_shadow[participant_name].add_shadow_file(
+                    file_path)
             else:
-                self.file_path_shadow[participant_name] = Participant(participant_name, file_path)
+                self.file_path_shadow[participant_name] = Participant(
+                    participant_name, file_path)