constants.py

import pandas as pd
from .preprocess import load_test_data

# Column names.
CSV_HEADER = [
    "age",
    "class_of_worker",
    "detailed_industry_recode",
    "detailed_occupation_recode",
    "education",
    "wage_per_hour",
    "enroll_in_edu_inst_last_wk",
    "marital_stat",
    "major_industry_code",
    "major_occupation_code",
    "race",
    "hispanic_origin",
    "sex",
    "member_of_a_labor_union",
    "reason_for_unemployment",
    "full_or_part_time_employment_stat",
    "capital_gains",
    "capital_losses",
    "dividends_from_stocks",
    "tax_filer_stat",
    "region_of_previous_residence",
    "state_of_previous_residence",
    "detailed_household_and_family_stat",
    "detailed_household_summary_in_household",
    "instance_weight",
    "migration_code-change_in_msa",
    "migration_code-change_in_reg",
    "migration_code-move_within_reg",
    "live_in_this_house_1_year_ago",
    "migration_prev_res_in_sunbelt",
    "num_persons_worked_for_employer",
    "family_members_under_18",
    "country_of_birth_father",
    "country_of_birth_mother",
    "country_of_birth_self",
    "citizenship",
    "own_business_or_self_employed",
    "fill_inc_questionnaire_for_veterans_admin",
    "veterans_benefits",
    "weeks_worked_in_year",
    "year",
    "income_level",
]

# Target feature name.
TARGET_FEATURE_NAME = "income_level"

# Weight column name.
WEIGHT_COLUMN_NAME = "instance_weight"

# Numeric feature names.
NUMERIC_FEATURE_NAMES = [
    "age",
    "wage_per_hour",
    "capital_gains",
    "capital_losses",
    "dividends_from_stocks",
    "num_persons_worked_for_employer",
    "weeks_worked_in_year",
]

##Cols which will use "Number" component of gradio for taking user input
NUMBER_INPUT_COLS = ['age', 'num_persons_worked_for_employer','weeks_worked_in_year']

test_data = load_test_data()

CATEGORICAL_FEATURES_WITH_VOCABULARY = {
    feature_name: sorted([str(value) for value in list(test_data[feature_name].unique())])
    for feature_name in CSV_HEADER
    if feature_name
    not in list(NUMERIC_FEATURE_NAMES + [WEIGHT_COLUMN_NAME, TARGET_FEATURE_NAME])
}
# All features names.
FEATURE_NAMES = NUMERIC_FEATURE_NAMES + list(
    CATEGORICAL_FEATURES_WITH_VOCABULARY.keys()
)
# Feature default values.
COLUMN_DEFAULTS = [
    [0.0]
    if feature_name in NUMERIC_FEATURE_NAMES + [TARGET_FEATURE_NAME, WEIGHT_COLUMN_NAME]
    else ["NA"]
    for feature_name in CSV_HEADER
]