import pandas as pd import numpy as np import plotly.graph_objects as go import plotly.express as px import json from collections import Counter pd.options.plotting.backend = "plotly" from IPython.display import HTML

path = 'mkturk_results_100520.csv'

# from IPython.display import HTML # HTML('''<script> # let code_show=true; # function code_toggle() { # if (code_show){ # console.log("yay") # } else { # console.log("naw") # } # code_show = !code_show # } # </script> # <form action="javascript:code_toggle()"><input type="submit" value="Toggle"></form>''')

# from IPython.display import display, HTML # js = "<script>console.log('Hello World!');</script>" # display(HTML(js))

def build_df(path): '''Takes in path to csv file of mkturk results, seperates data into a list of individual series and returns a dataframe of just the user responses''' data = pd.read_csv(path) task_answers = data['Answer.taskAnswers'].values answer_dicts = [json.loads(task_answers[i].strip("[,]")) for i in range(len(task_answers))] cols = answer_dicts[0].keys() df = pd.DataFrame(columns=cols) for index, item in enumerate(answer_dicts): df.loc[len(df)] = answer_dicts[index] return df

s4s4 = task_answers_df['s4s3'].copy()

rm_from_slide_4 = ['episodes','offspring','grace-and-frankie','onde-day-at-at-time','fuller-house']

new_top_titles_s4s3 = [] for responses in s4s4: new_list = {key:val for key,val in responses.items() if key in rm_from_slide_4} new_top_titles_s4s3.append(new_list) task_answers_df['s4s3'] = pd.Series(new_top_titles_s4s3)

new_top_titles_s4s4 = [] for items in s4s4: new_list = {key:val for key,val in responses.items() if key not in rm_from_slide_4} new_top_titles_s4s4.append(new_list) task_answers_df['s4s4'] = pd.Series(new_top_titles_s4s4)

def surface_selections(df,df_column): '''Takes in a pandas series and returns a new cleaned one removing false (non selected) items''' selected_titles = [] for all_titles in df[df_column].values: selections = [title for title, val in all_titles.items() if val == True] selected_titles.append(selections) # clean_series = pd.Series(selected_titles) clean_series = pd.Series(selected_titles).apply(lambda val: np.NaN if len(val)==0 else val) return clean_series

# columns we know have the format of {title: bool} we need to clean cols_to_clean = [ 's2s1', 's2s2', 's2s3', 's2s4', 's4s1', 's4s2', 's4s3', 's4s4', 's5s1', 's5s2', 's5s3', 's5s4' ]

for col in cols_to_clean: task_answers_df[col] = surface_selections(task_answers_df,col)

def get_toggle_val(df,df_column): '''Takes in a pandas series and returns a new cleaned one leaving only boolean state''' return df[df_column].apply(lambda val: val.get('on'))

task_answers_df['s3t1'] = get_toggle_val(task_answers_df,'s3t1')

def get_top_responses(column): return [(key,val) for key, val in task_answers_df[column].value_counts().items()]

def plot_freq(top_responses, title): keys = pd.Series([title[0] for title in top_responses])[:10] count = pd.Series([title[1] for title in top_responses])[:10] freq_count = pd.DataFrame({'Title': keys,'Count':count}) fig = px.histogram(freq_count,x='Title', y ='Count', title=title) fig.update_xaxes(type='category') fig.show()

def get_title_frequency(column): top_selections = [] for selection in task_answers_df[column].values: if type(selection) == list: for title in selection: top_selections.append(title) else: top_selections.append(selection) return pd.Series(top_selections).value_counts()