Use bomb_risk_density.csv

app.py

@@ -1,146 +1,8 @@
-import os
-import json
 import pandas as pd
-from collections import defaultdict, Counter
 import altair as alt
 import panel as pn
 
-
-def choices_to_df(choices, hue):
-    df = pd.DataFrame(choices, columns=['choices'])
-    df['hue'] = hue
-    df['hue'] = df['hue'].astype(str)
-    return df
-
-def arrange_data():
-    
-    # Human Data
-    
-    df = pd.read_csv('Project/2_scientific/ChatGPT-Behavioral-main/data/bomb_risk.csv')
-    df = df[df['Role'] == 'player']
-    df = df[df['gameType'] == 'bomb_risk']
-    df.sort_values(by=['UserID', 'Round'])
-
-    prefix_to_choices_human = defaultdict(list)
-    prefix_to_IPW = defaultdict(list)
-    prev_user = None
-    prev_move = None
-    prefix = ''
-    bad_user = False
-    for _, row in df.iterrows():
-        if bad_user: continue
-        if row['UserID'] != prev_user:
-            prev_user = row['UserID']
-            prefix = ''
-            bad_user = False
-
-        move = row['move']
-        if move < 0 or move > 100:
-            bad_users = True
-            continue
-        prefix_to_choices_human[prefix].append(move)
-
-        if len(prefix) == 0:
-            prefix_to_IPW[prefix].append(1)
-        elif prefix[-1] == '1':
-            prev_move = min(prev_move, 98)
-            prefix_to_IPW[prefix].append(1./(100 - prev_move))
-        elif prefix[-1] == '0':
-            prev_move = max(prev_move, 1)
-            prefix_to_IPW[prefix].append(1./(prev_move))
-        else: assert False
-        
-        prev_move = move
-
-        prefix += '1' if row['roundResult'] == 'SAFE' else '0'
-
-
-    # Model Data
-        
-    prefix_to_choices_model = defaultdict(lambda : defaultdict(list))
-    for model in ['ChatGPT-4', 'ChatGPT-3']:
-        if model == 'ChatGPT-4':
-            file_names = [
-                'bomb_gpt4_2023_05_15-12_13_51_AM.json'
-            ]
-        elif model == 'ChatGPT-3':
-            file_names = [
-                'bomb_turbo_2023_05_14-10_45_50_PM.json'
-            ]
-
-        choices = []
-        scenarios = []
-        for file_name in file_names:
-            with open(os.path.join('Project/2_scientific/ChatGPT-Behavioral-main/records', file_name), 'r') as f:
-                records = json.load(f)
-                choices += records['choices']
-                scenarios += records['scenarios']
-
-        assert len(scenarios) == len(choices)
-        print('loaded %i valid records' % len(scenarios))
-
-        prefix_to_choice = defaultdict(list)
-        prefix_to_result = defaultdict(list)
-        prefix_to_pattern = defaultdict(Counter)
-        wrong_sum = 0
-        for scenarios_tmp, choices_tmp in zip(scenarios, choices):
-
-            result = 0
-            for i, scenario in enumerate(scenarios_tmp):
-                prefix = tuple(scenarios_tmp[:i])
-                prefix = ''.join([str(x) for x in prefix])
-                choice = choices_tmp[i]
-                
-                prefix_to_choice[prefix].append(choice)
-                prefix_to_pattern[prefix][tuple(choices_tmp[:-1])] += 1
-
-                prefix = tuple(scenarios_tmp[:i+1])
-                if scenario == 1:
-                    result += choice
-                prefix_to_result[prefix].append(result)
-
-        print('# of wrong sum:', wrong_sum)
-        print('# of correct sum:', len(scenarios) - wrong_sum)
-
-        prefix_to_choices_model[model] = prefix_to_choice
-
-
-    # Arrange Data
-
-    round_dict = {'': [1, -1, -1],
-                '0': [2, 0, -1],
-                '1': [2, 1, -1],
-                '00': [3, 0, 0],
-                '01': [3, 0, 1],
-                '10': [3, 1, 0],
-                '11': [3, 1, 1]}
-
-    df_bomb_all = pd.DataFrame()
-
-    for prefix in round_dict:
-        
-        df_bomb_human = choices_to_df(prefix_to_choices_human[prefix], hue='Human')
-        df_bomb_human['weight'] = prefix_to_IPW[prefix]
-        
-        df_bomb_models = pd.concat([choices_to_df(
-                prefix_to_choices_model[model][prefix], hue=model
-            ) for model in prefix_to_choices_model]
-        )
-        df_bomb_models['weight'] = 1    
-        
-        df_bomb_temp = pd.concat([df_bomb_human, df_bomb_models])
-        df_bomb_temp['prefix'] = prefix
-
-        df_bomb_all = pd.concat([df_bomb_all, df_bomb_temp])
-
-    df_density = df_bomb_all.groupby(['hue', 'prefix'])['choices'].value_counts(normalize=True).unstack(fill_value=0).stack().reset_index()
-    df_density = df_density.rename(columns={'hue': 'Subject', 'choices': 'Boxes', 0: 'Density'})
-    df_density['Round'] = df_density['prefix'].apply(lambda x: round_dict[x][0])
-    
-    return df_density
-
-
-df_density = arrange_data()
+df_density = pd.read_csv('Project/2_scientific/bomb_risk_density.csv', dtype={'prefix': str})
 alt.data_transformers.disable_max_rows()
 
 # Enable Panel extensions
@@ -161,7 +23,7 @@ def create_plot(bomb_1, bomb_2):
     range_ = ['#009FB7', '#FED766', '#FE4A49']
 
     plot = alt.Chart(df_density).transform_filter(
-        (alt.datum.prefix == '') | (alt.datum.prefix == str(bomb_1)) | (alt.datum.prefix == str(bomb_1) + str(bomb_2))
+        (alt.datum.prefix == '-1') | (alt.datum.prefix == str(bomb_1)) | (alt.datum.prefix == str(bomb_1) + str(bomb_2))
     ).mark_bar(opacity=0.5).encode(
         x=alt.X('Boxes:Q', 
                 bin=alt.Bin(maxbins=10),