| import gradio as gr | |
| from collections import OrderedDict | |
| import numpy as np | |
| from huggingface_hub import from_pretrained_keras | |
| def predict( | |
| age,workclass,fnlwgt,education,education_num,marital_status,occupation,relationship, | |
| race,gender,capital_gain,capital_loss,hours_per_week,native_country | |
| ): | |
| user_data = {} | |
| user_data['age'] = np.array([age],dtype=np.float32) | |
| user_data['workclass'] = np.array([f'{workclass}'],dtype="object") | |
| user_data['fnlwgt'] = np.array([fnlwgt],dtype=np.float32) | |
| user_data['education'] = np.array([f'{education}'],dtype="object") | |
| user_data['education_num'] = np.array([education_num],dtype=np.float32) | |
| user_data['marital_status'] = np.array([f'{marital_status}'],dtype="object") | |
| user_data['occupation'] = np.array([f'{occupation}'],dtype="object") | |
| user_data['relationship'] = np.array([f'{relationship}'],dtype="object") | |
| user_data['race'] = np.array([f'{race}'],dtype="object") | |
| user_data['gender'] = np.array([f'{gender}'],dtype="object") | |
| user_data['capital_gain'] = np.array([capital_gain],dtype=np.float32) | |
| user_data['capital_loss'] = np.array([capital_loss],dtype=np.float32) | |
| user_data['hours_per_week'] = np.array([hours_per_week],dtype=np.float32) | |
| user_data['native_country'] = np.array([f'{native_country}'],dtype="object") | |
| test_user_data = OrderedDict(user_data) | |
| model = from_pretrained_keras("keras-io/neural-decision-forest") | |
| pred = model.predict(test_user_data) | |
| pred = np.argmax(pred,axis=1) | |
| return f"Outcome: {pred}" | |
| work_class_list = [' Self-emp-not-inc', ' Private', ' State-gov', ' Federal-gov',' Local-gov', ' ?', ' Self-emp-inc', ' Without-pay',' Never-worked'] | |
| education_list = [' Bachelors', ' HS-grad', ' 11th', ' Masters', ' 9th',' Some-college', ' Assoc-acdm', ' Assoc-voc', ' 7th-8th',' Doctorate', ' Prof-school', ' 5th-6th', ' 10th', ' 1st-4th',' Preschool', ' 12th'] | |
| martial_list = [' Married-civ-spouse',' Divorced',' Married-spouse-absent',' Never-married',' Separated',' Married-AF-spouse',' Widowed'] | |
| race_list = [' White',' Black',' Asian-Pac-Islander',' Amer-Indian-Eskimo',' Other'] | |
| relation_list = [' Husband',' Not-in-family',' Wife',' Own-child',' Unmarried',' Other-relative'] | |
| occupation_list = [' Exec-managerial',' Handlers-cleaners',' Prof-specialty',' Other-service',' Adm-clerical',' Sales',' Craft-repair',' Transport-moving',' Farming-fishing',' Machine-op-inspct',' Tech-support',' ?',' Protective-serv',' Armed-Forces',' Priv-house-serv'] | |
| countries = [' United-States',' Cuba',' Jamaica',' India',' Mexico',' South',' Puerto-Rico',' Honduras',' England',' Canada',' Germany',' Iran',' Philippines',' Italy',' Poland',' Columbia',' Cambodia',' Thailand',' Ecuador',' Laos',' Taiwan',' Haiti',' Portugal',' Dominican-Republic',' El-Salvador',' France',' Guatemala',' China',' Japan',' Yugoslavia',' Peru',' Outlying-US(Guam-USVI-etc)',' Scotland',' Trinadad&Tobago',' Greece',' Nicaragua',' Vietnam',' Hong',' Ireland',' Hungary',' Holand-Netherlands'] | |
| title = "Deep Neural Decision Forest" | |
| description = "This example uses the United States Census Income Dataset provided by the UC Irvine Machine Learning Repository. The task is binary classification to predict whether a person is likely to be making over USD 50,000 a year." | |
| article = """<p style='text-align: center'> | |
| <a href='https://keras.io/examples/structured_data/deep_neural_decision_forests/' target='_blank'>Keras Example given by Khalid Salama</a> | |
| <br/> | |
| <a href="https://huggingface.co/lucifertrj">Space by @lucifertrj</a> | |
| </p> | |
| """ | |
| demo = gr.Interface( | |
| predict, | |
| [ | |
| gr.Slider(12, 85, value=1), | |
| gr.Dropdown(work_class_list), | |
| gr.Slider(1260, 12225, value=200), | |
| gr.Dropdown(education_list), | |
| gr.Slider(1, 16, value=2), | |
| gr.Dropdown(martial_list), | |
| gr.Dropdown(occupation_list), | |
| gr.Dropdown(relation_list), | |
| gr.Dropdown(race_list), | |
| gr.Dropdown([' Male',' Female']), | |
| gr.Slider(0, 10000, value=100), | |
| gr.Slider(0, 4500, value=75), | |
| gr.Slider(1, 100, value=2), | |
| gr.Dropdown(countries), | |
| ], | |
| outputs = "text", | |
| title = title, | |
| description = description, | |
| article = article, | |
| examples= | |
| [ | |
| [35,' Private',5000,' Masters',8,' Divorced',' Tech-support',' Husband',' White',' Male',6000,0,40,' Germany'], | |
| [27,' Self-emp-inc',2400,' Bachelors',6,' Separated',' Prof-specialty',' Wife',' Amer-Indian-Eskimo',' Female',4000,1050,32,' England'], | |
| ] | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() |