US Feasibility Finder on the GPT Store

Introduction to US Feasibility Finder

GPT Description

GPT Prompt Starters

• Age Gender (BROAD) Feasibility 📊 🔍 👬📈 🧮 📉 💻 import pandas as pd # Load the dataset data = pd.read_csv('/mnt/data/Angus Reid Forum USA.csv') # Preparing the data data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') # Calculate feasibility feasibility = (data.groupby(['P_Region_FIP', 'Age x Gender Broad'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0)) # Reordering columns columns_order = ['Female 18-34', 'Female 35-54', 'Female 55 Plus', 'Male 18-34', 'Male 35-54', 'Male 55 Plus'] feasibility = feasibility[columns_order] # Adding row totals feasibility['Total'] = feasibility.sum(axis=1) # Reset index to display the regions feasibility.reset_index(inplace=True) # Adding column totals column_totals = feasibility.sum(numeric_only=True) column_totals['P_Region_FIP'] = 'Total' feasibility = feasibility.append(column_totals, ignore_index=True) # Display the feasibility table with row and column totals print(feasibility)
• Age Gender (GENERATION) Feasibility 👶🧒👧👵👴 - import pandas as pd # Load the dataset data = pd.read_csv('/mnt/data/Angus Reid Forum USA.csv') # Preparing the data with 'Generation' data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') data['Gender x Generation'] = data['Gender'] + " " + data['Generation'] # Calculate feasibility using combined 'Gender x Generation' category feasibility_gen = (data.groupby(['P_Region_FIP', 'Gender x Generation'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0)) # Sorting columns to have females on the left and males on the right columns_sorted_gen = sorted(feasibility_gen.columns, key=lambda x: (x.split()[0], x.split()[1])) feasibility_gen = feasibility_gen[columns_sorted_gen] # Adding row totals feasibility_gen['Total'] = feasibility_gen.sum(axis=1) # Reset index to display the regions feasibility_gen.reset_index(inplace=True) # Adding column totals column_totals_gen = feasibility_gen.sum(numeric_only=True) column_totals_gen['P_Region_FIP'] = 'Total' feasibility_gen = feasibility_gen.append(column_totals_gen, ignore_index=True) # Display the feasibility table with row and column totals print(feasibility_gen)
• Age Gender (FINE) Feasibility 📊 🔍 👬📈 🧮 📉 💻 - import pandas as pd # Load the dataset data = pd.read_csv('/mnt/data/Angus Reid Forum USA.csv') # Preparing the data data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') data['Gender x Age Fine'] = data['Gender'] + " " + data['Age Fine'] # Calculate feasibility using combined 'Gender x Age Fine' category feasibility = (data.groupby(['P_Region_FIP', 'Gender x Age Fine'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0)) # Sorting columns to have females on the left and males on the right columns_sorted = sorted(feasibility.columns, key=lambda x: (x.split()[0], x.split()[1])) feasibility = feasibility[columns_sorted] # Adding row totals feasibility['Total'] = feasibility.sum(axis=1) # Reset index to display the regions feasibility.reset_index(inplace=True) # Adding column totals column_totals = feasibility.sum(numeric_only=True) column_totals['P_Region_FIP'] = 'Total' feasibility = feasibility.append(column_totals, ignore_index=True) # Save or display the feasibility table with row and column totals print(feasibility)
• Employment Status Feasibility 💼📈🤝🏢💲📉 💻 - import pandas as pd def calculate_feasibility(csv_file_path, region_col, employment_col, response_rate_col, employment_order): # Load the dataset data = pd.read_csv(csv_file_path) # Convert the response rate to numeric, handling any non-numeric values data[response_rate_col] = pd.to_numeric(data[response_rate_col], errors='coerce') # Calculate feasibility feasibility = (data.groupby([region_col, employment_col])[response_rate_col] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0)[employment_order]) # Adding row totals feasibility['Total'] = feasibility.sum(axis=1) # Reset index to display the regions feasibility.reset_index(inplace=True) # Adding column totals column_totals = feasibility.sum(numeric_only=True) column_totals[region_col] = 'Total' feasibility = feasibility.append(column_totals, ignore_index=True) return feasibility # Parameters for the function csv_file_path = '/mnt/data/Angus Reid Forum USA.csv' # Path to your dataset region_col = 'P_Region_FIP' # Column name for region employment_col = "First, we would like to ask a few questions about your main job. Are you…?" # Employment status column response_rate_col = 'Response Rate' # Column name for response rate employment_order = [ 'A full-time employee', 'A part-time or contract employee', 'A business owner', 'Self-employed', 'Retired', 'Unemployed but looking for work', 'Unemployed and not looking for work', 'Other' # Exclude any category not present in your data ] # Calculate and display the feasibility table feasibility_table = calculate_feasibility(csv_file_path, region_col, employment_col, response_rate_col, employment_order) print(feasibility_table)
• VizMin Feasibility 👩🏿‍🦳👨🏾‍🦱👳👩🏻🧑🏽🧕 - import pandas as pd # Load the dataset data = pd.read_csv('/mnt/data/Angus Reid Forum USA.csv') # Preparing the data data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') data['Viz Min'].fillna('Not Specified', inplace=True) # Calculate feasibility with "Viz Min" nested within gender feasibility_viz_min = (data.groupby(['P_Region_FIP', 'Gender', 'Viz Min'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(level=[1, 2], fill_value=0)) # Preparing the columns order based on gender and Viz Min viz_min_categories = data['Viz Min'].unique() columns_order_viz_min = [(gender, viz_min) for gender in ['Female', 'Male'] for viz_min in viz_min_categories] feasibility_viz_min = feasibility_viz_min.reindex(columns=columns_order_viz_min, fill_value=0) # Adding row totals feasibility_viz_min['Total'] = feasibility_viz_min.sum(axis=1) # Reset index to display the regions feasibility_viz_min.reset_index(inplace=True) # Adding column totals column_totals_viz_min = feasibility_viz_min.sum(numeric_only=True) column_totals_viz_min['P_Region_FIP'] = 'Total' feasibility_viz_min = feasibility_viz_min.append(column_totals_viz_min, ignore_index=True) # Display the feasibility table with Viz Min nested within gender print(feasibility_viz_min)
• Household Income Feasibility - 😄 🤑 💰 💎 - import pandas as pd # Load the dataset data = pd.read_csv('/mnt/data/Angus Reid Forum USA.csv') # Preparing the data data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') income_column = "Which of the following ranges best describes your total annual household income before taxes?" # Calculate feasibility for household income income_feasibility = (data.groupby(['P_Region_FIP', income_column])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0)) # Sorting columns in ascending order of income ranges income_feasibility = income_feasibility.sort_index(axis=1) # Adding row totals income_feasibility['Total'] = income_feasibility.sum(axis=1) # Reset index to display the regions income_feasibility.reset_index(inplace=True) # Adding column totals income_column_totals = income_feasibility.sum(numeric_only=True) income_column_totals['P_Region_FIP'] = 'Total' income_feasibility = income_feasibility.append(income_column_totals, ignore_index=True) # Display the feasibility table with row and column totals print(income_feasibility)
• Education Feasibility -🎓 📚 📖 ✏️ 📝 import pandas as pd # Load the dataset data = pd.read_csv('/mnt/data/Angus Reid Forum USA.csv') # Preparing the data data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') # Calculate feasibility for Education Broad category feasibility_education = (data.groupby(['P_Region_FIP', 'Education Broad'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0)) # Adding row totals feasibility_education['Total'] = feasibility_education.sum(axis=1) # Reset index to display the regions feasibility_education.reset_index(inplace=True) # Adding column totals column_totals_education = feasibility_education.sum(numeric_only=True) column_totals_education['P_Region_FIP'] = 'Total' feasibility_education = feasibility_education.append(column_totals_education, ignore_index=True) # Display the feasibility table with Education Broad category print(feasibility_education)
• Age Gender (BROAD) + Education Feasibility 👬🎓 📚 📖 ✏️ 📝-import pandas as pd # Load the dataset data = pd.read_csv('/mnt/data/Angus Reid Forum USA.csv') # Original file path # Prepare the data by converting 'Response Rate' to numeric, handling non-numeric values data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') # Calculate feasibility for Age x Gender Broad category feasibility_age_gender = ( data.groupby(['P_Region_FIP', 'Age x Gender Broad'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0) ) # Reordering columns for Age x Gender Broad columns_order_age_gender = [ 'Female 18-34', 'Female 35-54', 'Female 55 Plus', 'Male 18-34', 'Male 35-54', 'Male 55 Plus' ] feasibility_age_gender = feasibility_age_gender[columns_order_age_gender] # Rename columns for clarity in the merged table feasibility_age_gender.columns = [f'AGB_{col}' for col in feasibility_age_gender.columns] # Calculate feasibility for Education Broad category feasibility_education = ( data.groupby(['P_Region_FIP', 'Education Broad'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0) ) # Rename columns for clarity in the merged table feasibility_education.columns = [ f'EDU_{col}' if col != 'P_Region_FIP' else col for col in feasibility_education.columns ] # Correctly merging the two tables on 'P_Region_FIP' merged_feasibility = pd.merge(feasibility_age_gender.reset_index(), feasibility_education.reset_index(), on='P_Region_FIP') # Swapping the order of the columns "College" with "High School or Less" columns_reordered = ['P_Region_FIP', 'AGB_Female 18-34', 'AGB_Female 35-54', 'AGB_Female 55 Plus', 'AGB_Male 18-34', 'AGB_Male 35-54', 'AGB_Male 55 Plus', 'EDU_High school or less', 'EDU_College', 'EDU_University Plus'] merged_feasibility_reordered = merged_feasibility[columns_reordered] # Calculating column totals (excluding the region column) for the reordered table column_totals_reordered = merged_feasibility_reordered.iloc[:, 1:].sum().rename('Total') merged_feasibility_with_totals_reordered = merged_feasibility_reordered.append(column_totals_reordered, ignore_index=True) # Setting the 'P_Region_FIP' for the totals row merged_feasibility_with_totals_reordered.at[len(merged_feasibility_with_totals_reordered) - 1, 'P_Region_FIP'] = 'Total' # Display the table with reordered columns print(merged_feasibility_with_totals_reordered)
• Race Feasibility - 👩🏿👲👳🧕👨‍🦱 👩‍🦰 - import pandas as pd # Load the dataset file_path = '/mnt/data/Angus Reid Forum USA.csv' # Specific file path and name data = pd.read_csv(file_path) # Preparing the data data['Response Rate'] = pd.to_numeric(data['Response Rate'], errors='coerce') # Calculate feasibility based on Race race_feasibility = (data.groupby(['P_Region_FIP', 'Race'])['Response Rate'] .apply(lambda x: int((x.count() * x.mean()))) .unstack(fill_value=0)) # Sort the columns by their total frequency in descending order and adjust the order race_totals = race_feasibility.sum().sort_values(ascending=False) sorted_columns = race_totals.index.tolist() # Move 'Two or more races' and 'Some other race' to the end sorted_columns.remove('Two or more races') sorted_columns.remove('Some other race') sorted_columns += ['Two or more races', 'Some other race'] # Move 'Other Asian' after 'Vietnamese' other_asian_index = sorted_columns.index('Other Asian [e.g. Cambodian, Indonesian]') vietnamese_index = sorted_columns.index('Vietnamese') sorted_columns.insert(vietnamese_index + 1, sorted_columns.pop(other_asian_index)) # Reorder the feasibility table according to the adjusted column order race_feasibility = race_feasibility[sorted_columns] # Adding row totals race_feasibility['Total'] = race_feasibility.sum(axis=1) # Reset index to display the regions race_feasibility.reset_index(inplace=True) # Display the race feasibility table with row and column totals print(race_feasibility)