| import gradio as gr |
| import tensorflow as tf |
| import numpy as np |
|
|
| |
| model = tf.keras.models.load_model("census.h5") |
|
|
| |
| mapping = { |
| 'workclass': {' ?': 0, ' Federal-gov': 1, ' Local-gov': 2, ' Never-worked': 3, ' Private': 4, ' Self-emp-inc': 5, ' Self-emp-not-inc': 6, ' State-gov': 7, ' Without-pay': 8}, |
| 'education': {' 10th': 0, ' 11th': 1, ' 12th': 2, ' 1st-4th': 3, ' 5th-6th': 4, ' 7th-8th': 5, ' 9th': 6, ' Assoc-acdm': 7, ' Assoc-voc': 8, ' Bachelors': 9, ' Doctorate': 10, ' HS-grad': 11, ' Masters': 12, ' Preschool': 13, ' Prof-school': 14, ' Some-college': 15}, |
| 'marital_status': {' Divorced': 0, ' Married-AF-spouse': 1, ' Married-civ-spouse': 2, ' Married-spouse-absent': 3, ' Never-married': 4, ' Separated': 5, ' Widowed': 6}, |
| 'occupation': {' ?': 0, ' Adm-clerical': 1, ' Armed-Forces': 2, ' Craft-repair': 3, ' Exec-managerial': 4, ' Farming-fishing': 5, ' Handlers-cleaners': 6, ' Machine-op-inspct': 7, ' Other-service': 8, ' Priv-house-serv': 9, ' Prof-specialty': 10, ' Protective-serv': 11, ' Sales': 12, ' Tech-support': 13, ' Transport-moving': 14}, |
| 'relationship': {' Husband': 0, ' Not-in-family': 1, ' Other-relative': 2, ' Own-child': 3, ' Unmarried': 4, ' Wife': 5}, |
| 'race': {' Amer-Indian-Eskimo': 0, ' Asian-Pac-Islander': 1, ' Black': 2, ' Other': 3, ' White': 4}, |
| 'gender': {' Female': 0, ' Male': 1}, |
| 'native_country': {' ?': 0, ' Cambodia': 1, ' Canada': 2, ' China': 3, ' Columbia': 4, ' Cuba': 5, ' Dominican-Republic': 6, ' Ecuador': 7, ' El-Salvador': 8, ' England': 9, ' France': 10, ' Germany': 11, ' Greece': 12, ' Guatemala': 13, ' Haiti': 14, ' Honduras': 15, ' Hong': 16, ' Hungary': 17, ' India': 18, ' Iran': 19, ' Ireland': 20, ' Italy': 21, ' Jamaica': 22, ' Japan': 23, ' Laos': 24, ' Mexico': 25, ' Nicaragua': 26, ' Outlying-US(Guam-USVI-etc)': 27, ' Peru': 28, ' Philippines': 29, ' Poland': 30, ' Portugal': 31, ' Puerto-Rico': 32, ' Scotland': 33, ' South': 34, ' Taiwan': 35, ' Thailand': 36, ' Trinadad&Tobago': 37, ' United-States': 38, ' Vietnam': 39, ' Yugoslavia': 40} |
| } |
|
|
| |
| def salarybracket(age, workclass, education, education_num, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country): |
| |
| workclass_value = next((v for k, v in mapping['workclass'].items() if k == workclass), None) |
| education_value = next((v for k, v in mapping['education'].items() if k == education), None) |
| marital_status_value = next((v for k, v in mapping['marital_status'].items() if k == marital_status), None) |
| occupation_value = next((v for k, v in mapping['occupation'].items() if k == occupation), None) |
| relationship_value = next((v for k, v in mapping['relationship'].items() if k == relationship), None) |
| race_value = next((v for k, v in mapping['race'].items() if k == race), None) |
| gender_value = next((v for k, v in mapping['gender'].items() if k == gender), None) |
| native_country_value = next((v for k, v in mapping['native_country'].items() if k == native_country), None) |
| |
| inputs = np.array([[age, workclass_value, education_value, education_num, marital_status_value, occupation_value, relationship_value, race_value, gender_value, capital_gain, capital_loss, hours_per_week, native_country_value]]) |
| prediction = model.predict(inputs) |
| prediction_value = prediction[0][0] |
| result = "Income_bracket lesser than or equal to 50K ⬇️" if prediction_value <= 0.5 else "Income_bracket greater than 50K ⬆️" |
| return f"{result}" |
|
|
| |
| dropdown_options = {} |
| for column, values in mapping.items(): |
| options = [] |
| for label, value in values.items(): |
| options.append(label) |
| dropdown_options[column] = options |
|
|
| |
| salarybracket_ga = gr.Interface(fn=salarybracket, |
| inputs=[ |
| gr.Slider(17, 90, label="Age"), |
| gr.Dropdown(dropdown_options['workclass'], label="Workclass"), |
| gr.Dropdown(dropdown_options['education'], label="Education"), |
| gr.Number(1, 16, label="Education Num [1 to 16]"), |
| gr.Dropdown(dropdown_options['marital_status'], label="Marital Status"), |
| gr.Dropdown(dropdown_options['occupation'], label="Occupation"), |
| gr.Dropdown(dropdown_options['relationship'], label="Relationship"), |
| gr.Dropdown(dropdown_options['race'], label="Race"), |
| gr.Dropdown(dropdown_options['gender'], label="Gender"), |
| gr.Number(0, 99999, label="Capital Gain [0 to 99999]"), |
| gr.Number(0, 4356, label="Capital Loss [0 to 4356]"), |
| gr.Number(1, 99, label="Hours per Week [1 to 99]"), |
| gr.Dropdown(dropdown_options['native_country'], label="Native Country") |
| ], |
| outputs="text", |
| examples = [ |
| [28,Private,Bachelors,13,Married-civ-spouse,Prof-specialty,Wife,Black,Female,0,0,40,Cuba], |
| [38,Private,Some-college,10,Divorced,Craft-repair,Own-child,White,Male,0,0,58,Poland], |
| [44,Private,Some-college,10,Married-civ-spouse,Transport-moving,Husband,White,Male,0,0,40,United-States], |
| [29,Private,HS-grad,9,Never-married,Machine-op-inspct,Own-child,Asian-Pac-Islander,Male,0,0,40,Germany], |
| [31,Private,HS-grad,9,Separated,Machine-op-inspct,Unmarried,White,Female,0,2238,40,United-States], |
| ], |
| title="Salary Bracket Prediction", |
| description="Predicting Income Bracket Using TensorFlow", |
| theme='dark' |
| ) |
|
|
| salarybracket_ga.launch(share=True, debug=True) |
|
|
