adds ngram-pattern

src/read_logs.py

@@ -57,6 +57,12 @@ class LogAnalyser:
 
         self.update_df()
 
+    def get_ngram_pattern(self, s, n=2):
+        gnp = ''
+        for i in range(len(s)-(n-1)):
+            gnp += '1' if '1' in s[i:i+n] else '0'
+        return gnp
+
     def update_df(self):
         reaction_weight = set_input(self.container_param,
                                     label='Reaction Weight w', min_value=0.0, max_value=1.0, value=0.5, step=0.01,
@@ -76,16 +82,25 @@ class LogAnalyser:
             "Table Style:", ["Dataframe", "Table"])
         self.show_pe_data = self.container_param.checkbox(
             'Show Probability Emote', value=True, key='show_pe_data_log')
+        self.score_threshold = set_input(self.container_param,
+                                         label='Score Threshold', min_value=0.0, max_value=1.0, value=0.5, step=0.01,
+                                         key_slider='score_threshold_slider', key_input='score_threshold_input',)
+
         df_reaction_pattern = pd.DataFrame()
         reaction_pattern_dict = dict()
         for story_id in self.df.Story.unique():
             reaction_num = 0
+            reaction_frequency = 0
+            probability_emote = 0
+            random_value = 0
+            reaction_show = False
+
             def get_subset_condition(data):
                 return (data.Story == story_id) & (data.Turn == 'user')
             subset_condition = get_subset_condition(self.df)
             dfs = self.df[subset_condition]
             for i, (index, row) in enumerate(dfs.iterrows()):
-                if row.Emotion == 'neutral':
+                if row.Emotion == 'neutral' or row.Score < self.score_threshold:
                     reaction_show = False
                 else:
                     reaction_frequency = reaction_num/(i+1)
@@ -102,13 +117,19 @@ class LogAnalyser:
                 self.df.at[index, 'random_value'] = random_value
                 self.df.at[index, 'reaction_show'] = reaction_show
             s = ''
-            df_edit = self.df[get_subset_condition(self.df)].reaction_show.copy()
-            df_edit=df_edit.dropna()
+            df_edit = self.df[get_subset_condition(
+                self.df)].reaction_show.copy()
+            df_edit = df_edit.dropna()
             for v in df_edit:
                 s += str(int(v))
             # df_reaction_pattern.at[story_id]
             # reaction_pattern_dict['story_id']=story_id
-            reaction_pattern_dict['reaction_pattern']=s
+            reaction_pattern_dict['reaction_length'] = len(s)
+            reaction_pattern_dict['reaction_1'] = s.count('1')
+            reaction_pattern_dict['reaction_pattern'] = s
+
+            for i in range(2, 8):
+                reaction_pattern_dict[f'{i}-gram_pattern'] = self.get_ngram_pattern(s, n=i)
             df_reaction_pattern = pd.concat(
                 [df_reaction_pattern, pd.DataFrame(reaction_pattern_dict, index=[f'Story_{story_id}'])])
             # st.markdown(df_edit)
@@ -132,27 +153,31 @@ class LogAnalyser:
             dfs = dfs.apply(self.rower, axis=None)
             dfs = dfs.set_table_styles([{
                 'selector': 'tr:hover',
-                'props': 'font-size: 1.01em;'  # background-color: #eeee66;
+                'props': 'color: #000000'  # background-color: #eeee66;font-size: 1.01em;
             }])   # .hide_index()
 
             if table_mode == 'Dataframe':
                 st.dataframe(dfs)
-                st.dataframe(df_reaction_pattern.iloc[story_id-1] )  # set_na_rep(" ").s
+                # set_na_rep(" ").s
+                # st.dataframe(df_reaction_pattern.iloc[story_id-1])
             elif table_mode == 'Table':
                 st.table(dfs)
-                st.table(df_reaction_pattern.iloc[story_id-1] ) 
+                # st.table(df_reaction_pattern.iloc[story_id-1])
             # print(dfs.render())
         if table_mode == 'Dataframe':
             st.dataframe(df_reaction_pattern)
         elif table_mode == 'Table':
             st.table(df_reaction_pattern)
 
-    @staticmethod
-    @st.cache
-    def dfstyle_color_text_col(s):
+    # @st.cache
+    def dfstyle_color_text_col(self, s):
         result = ['background-color: white']*len(s)
         if s.Emotion == 'neutral' and s.Turn == 'user':
-            result[2:-1] = ['color: #992222']+['color: #333333']+['color: #fcfcfc']*3
+            result[2:-1] = ['color: #992222'] + \
+                ['color: #333333']+['color: #fcfcfc']*3
+        if s.Score < self.score_threshold and s.Turn == 'user':
+            result[3:-1] = ['color: #992222'] + ['color: #fcfcfc']*3
+            printj.red(result)
         if s.reaction_show == 1:
             result[-1] = 'color: #222222'
         elif s.reaction_show == 0:

src/test.py

@@ -0,0 +1,44 @@
+# %%
+import pandas as pd
+import numpy as np
+
+np.random.seed(24)
+df = pd.DataFrame({'A': np.linspace(1, 10, 10)})
+
+df = pd.concat([df, pd.DataFrame(np.random.randn(10, 4), columns=list('BCDE'))],
+               axis=1)
+df.iloc[0, 2] = np.nan
+df['reaction_show'] = True
+df
+# %%
+s = ''
+for v in df.reaction_show:
+    s += str(int(v))
+s
+
+
+# %%
+s = '101100'
+g2p = ''
+for i in range(len(s)-1):
+    # print(i, i+2, s)
+    # print(s[0:2])
+    g2p += '1' if '1' in s[i:i+2] else '0'
+
+g2p
+
+
+# # def highlight_greaterthan(s,column):
+# #     is_max = pd.Series(data=False, index=s.index)
+# #     is_max[column] = s.loc[column] >= 1
+# #     return ['background-color: red' if is_max.any() else '' for v in is_max]
+
+# def highlight_greaterthan_1(s):
+#     if s.B > 1.0:
+#         return ['background-color: white']+['background-color: yellow']+['background-color: white']*3
+#     else:
+#         return ['background-color: white']*5
+
+
+# df.style.apply(highlight_greaterthan_1, axis=1)
+# %%