Update app.py

app.py

@@ -0,0 +1,67 @@
+import gradio.inputs
+import gradio as gr
+
+import pickle
+import pandas as pd
+import sklearn
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.preprocessing import OrdinalEncoder
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_selector as selector
+#from sklearn.ensemble import HistGradientBoostingClassifier
+
+
+with open('./model_leads.pck', 'rb') as f:
+    model = pickle.load(f)
+
+labels = ["No, no será cliente", "Sí, será un cliente"]
+
+def convert(lead_origin, lead_source, do_not_email, totalvisits,total_time_spent_on_website, page_views_per_visit, last_activity, 
+                     specialization, what_is_your_current_occupation, tags, city, a_free_copy_of_mastering_the_interview, last_notable_activity ):
+    #Se crea un dataframe con los datos enviados
+    df = pd.DataFrame()
+    df['lead_origin'] = [lead_origin]
+    df['lead_source'] = [lead_source]
+    df['do_not_email'] = [do_not_email]
+    df['totalvisits'] = [totalvisits]
+    df['total_time_spent_on_website'] = [total_time_spent_on_website]
+    df['page_views_per_visit'] = [page_views_per_visit]
+    df['last_activity'] = [last_activity]
+    df['specialization'] = [specialization]
+    df['what_is_your_current_occupation'] = [what_is_your_current_occupation]
+    df['tags'] = [tags]
+    df['city'] = [city]
+    df['a_free_copy_of_mastering_the_interview'] = [a_free_copy_of_mastering_the_interview]
+    df['last_notable_activity'] = [last_notable_activity]
+    #El modelo hace su predicción
+    prediction = model.predict_proba(df).flatten()
+    print(prediction)
+    #Se devuelve el percentaje que el modelo ha predicho para cada etiqueta
+    return {labels[i]: float(prediction[i]) for i in range(2)}
+    #return {"No, no será cliente": prediction[0], "Sí, será un cliente": prediction[1]}
+
+
+iface = gr.Interface(
+    fn=convert, 
+    inputs= [
+             gr.inputs.Dropdown(["landing_page_submission", "api", "lead_add_form", "lead_import"]),
+             gr.inputs.Dropdown(['olark_chat', 'organic_search', 'direct_traffic', 'google', 'referral_sites', 'reference', 'welingak_website', 'social_media' ,'others', 'live_chat']),
+             gr.inputs.Checkbox(),
+             gr.inputs.Slider(0, 150),
+             gr.inputs.Slider(0, 1000),
+             gr.inputs.Slider(0, 15),
+             gr.inputs.Dropdown(['page_visited_on_website', 'email_opened', 'others', 'converted_to_lead',  'olark_chat_conversation', 'email_bounced', 'email_link_clicked', 'form_submitted_on_website', 'sms_sent']),
+             gr.inputs.Dropdown(['not_specified', 'business_administration', 'media_and_advertising', 'management_specializations', 'travel_and_tourism', 'banking,_investment_and_insurance', 'international_business', 'e-commerce', 'services_excellence', 'rural_and_agribusiness', 'e-business']),
+             gr.inputs.Dropdown(['unemployed', 'student' ,'working_professional', 'businessman', 'other', 'housewife']),
+             gr.inputs.Dropdown(['interested_in_other_courses', 'ringing', 'will_revert_after_reading_the_email', 'not_specified', 'lost_to_eins', 'other_tags', 'busy', 'closed_by_horizzon', 'interested__in_full_time_mba',  'lateral_student']),
+             gr.inputs.Dropdown(['mumbai', 'thane_&_outskirts', 'other_metro_cities', 'other_cities',  'other_cities_of_maharashtra', 'tier_ii_cities']),
+             gr.inputs.Checkbox(),
+             gr.inputs.Dropdown(['modified', 'email_opened', 'page_visited_on_website',  'other_notable_activity', 'email_link_clicked', 'olark_chat_conversation',  'sms_sent']),
+    ],
+    outputs="label",
+    title="¿Se convetirá en cliente?",
+    description="Aplicación de aprendizaje automático que predice la probabilidad de que un potencial cliente contrate los servicios de nuestra empresa",
+)
+
+iface.launch()