Cargar Model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.pkl filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,389 @@
+import gradio as gr
+import pandas as pd
+import pickle
+
+
+# Define params names
+PARAMS_NAME = [
+        "Age",
+        "BusinessTravel",
+        "DailyRate",
+        "Department",
+        "DistanceFromHome",
+        "Education",
+        "EducationField",
+        "EnvironmentSatisfaction",
+        "Gender",
+        "HourlyRate",
+        "JobInvolvement",
+        "JobLevel",
+        "JobRole",
+        "JobSatisfaction",
+        "MaritalStatus",
+        "MonthlyIncome",
+        "MonthlyRate",
+        "NumCompaniesWorked",
+        "OverTime",
+        "PercentSalaryHike",
+        "PerformanceRating",
+        "RelationshipSatisfaction",
+        "StockOptionLevel",
+        "TotalWorkingYears",
+        "TrainingTimesLastYear",
+        "WorkLifeBalance",
+        "YearsAtCompany",
+        "YearsInCurrentRole",
+        "YearsSinceLastPromotion",
+        "YearsWithCurrManager"
+]
+
+           
+# Load model
+with open("model/model1.pkl", "rb") as f:
+    model = pickle.load(f)
+
+
+
+
+def predict(*args):
+    answer_dict = {}
+
+    for i in range(len(PARAMS_NAME)):
+        answer_dict[PARAMS_NAME[i]] = [args[i]]
+
+    # Crear dataframe
+    single_instance = pd.DataFrame.from_dict(answer_dict)
+
+    single_instance_numbers = single_instance
+    
+    for columna in single_instance_numbers:
+            # Verificar si el tipo de dato es "object"
+            if single_instance_numbers[columna].dtype == 'object':
+                # Obtener los valores únicos de la columna
+                valores_unicos = single_instance_numbers[columna].unique()
+                
+                # Crear un diccionario de reemplazo
+                diccionario_reemplazo = {valor: indice for indice, valor in enumerate(valores_unicos)}
+                
+                # Reemplazar los valores en la columna
+                single_instance_numbers[columna] = single_instance_numbers[columna].map(diccionario_reemplazo)
+
+
+    
+    prediction = model.predict(single_instance_numbers)
+
+    # Como sabemos el model nos devuelve los tipos de fraude 1, 2 y 3 en el response. Podemos devolver un response estilo semáforo.
+    
+    # Cast numpy.int64 to just a int
+    Attrition = int(prediction[0])
+
+
+    # Adaptación respuesta
+    response = Attrition
+    if Attrition == 1:
+        response = "Good idea, \n but not now, I am not atrittioned yet"
+    if Attrition == 0:
+        response = "🤯  \n OMG! PLEEEEEASE"
+
+
+    return response
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(
+        """
+        #   Attrition Prevention 🤯
+        """
+    )
+
+    with gr.Row():
+        with gr.Column():
+
+            gr.Markdown(
+                """
+                ## Insert your job data here please 🤓
+                """
+            )
+            
+            Age = gr.Slider(
+                label='Age',
+                minimum=18,
+                maximum=60,
+                step=1,
+                value=41
+            )
+
+            BusinessTravel = gr.Radio(
+                label='Business Travel',
+                choices=['Travel Rarely', 'Travel Frequently', 'Non-Travel'],
+                value='Travel Rarely',
+            )
+
+            DailyRate = gr.Slider(
+                label='Daily Rate',
+                minimum=102,
+                maximum=1499,
+                step=1,
+                value=1102
+            )
+
+            Department = gr.Radio(
+                label='Department',
+                choices=['Sales', 'Research & Development', 'Human Resources'],
+                value='Sales',
+            )
+
+            DistanceFromHome = gr.Slider(
+                label='Distance From Home',
+                minimum=1,
+                maximum=29,
+                step=1,
+                value=1
+            )
+
+            Education = gr.Dropdown(
+                label='Education',
+                choices=['College', 'Below College', 'Master', 'Bachelor', 'Doctor'],
+                multiselect=False,
+                value='Bachelor',
+            )
+
+            EducationField = gr.Dropdown(
+                label='Education Field',
+                choices=['Life Sciences', 'Other', 'Medical', 'Marketing', 'Technical Degree', 'Human Resources'],
+                multiselect=False,
+                value='Life Sciences',
+            )
+
+            EnvironmentSatisfaction = gr.Dropdown(
+                label='Environment Satisfaction',
+                choices=['Medium', 'High', 'Very High', 'Low'],
+                multiselect=False,
+                value='Medium',
+            )
+
+            Gender = gr.Radio(
+                label='Gender',
+                choices=['Female', 'Male'],
+                value='Female',
+            )
+
+            HourlyRate = gr.Slider(
+                label='Hourly Rate',
+                minimum=30,
+                maximum=100,
+                step=1,
+                value=94
+            )
+
+            JobInvolvement = gr.Dropdown(
+                label='Job Involvement',
+                choices=['High', 'Medium', 'Very High', 'Low'],
+                multiselect=False,
+                value='High',
+            )
+
+            JobLevel = gr.Radio(
+                label='Job Level',
+                choices=[2, 1, 3, 4, 5],
+                value=2,
+            )
+
+            JobRole = gr.Dropdown(
+                label='Job Role',
+                choices=['Sales Executive', 'Research Scientist', 'Laboratory Technician', 'Manufacturing Director', 'Healthcare Representative', 'Manager', 'Sales Representative', 'Research Director', 'Human Resources'],
+                multiselect=False,
+                value='Sales Executive',
+            )
+
+            JobSatisfaction = gr.Dropdown(
+                label='Job Satisfaction',
+                choices=['Very High', 'Medium', 'High', 'Low'],
+                multiselect=False,
+                value='High',
+            )
+
+            MaritalStatus = gr.Radio(
+                label='Marital Status',
+                choices=['Single', 'Married', 'Divorced'],
+                value='Single',
+            )
+
+            MonthlyIncome = gr.Slider(
+                label='Monthly Income',
+                minimum=1009,
+                maximum=19999,
+                step=1,
+                value=5993
+            )
+
+            MonthlyRate = gr.Slider(
+                label='Monthly Rate',
+                minimum=2094,
+                maximum=26999,
+                step=1,
+                value=19479
+            )
+
+            NumCompaniesWorked = gr.Slider(
+                label='Num Companies Worked',
+                minimum=0,
+                maximum=9,
+                step=1,
+                value=8
+            )
+
+            OverTime = gr.Radio(
+                label='Overtime',
+                choices=['Yes', 'No'],
+                value='Yes',
+            )
+
+            PercentSalaryHike = gr.Slider(
+                label='Percent Salary Hike',
+                minimum=11,
+                maximum=25,
+                step=1,
+                value=11
+            )
+
+            PerformanceRating = gr.Radio(
+                label='Performance Rating',
+                choices=['Excellent', 'Outstanding'],
+                value='Excellent',
+            )
+
+            RelationshipSatisfaction = gr.Dropdown(
+                label='Relationship Satisfaction',
+                choices=['Low', 'Very High', 'Medium', 'High'],
+                multiselect=False,
+                value='Low',
+            )
+
+            StockOptionLevel = gr.Radio(
+                label='Stockoption Level',
+                choices=[0, 1, 3, 2],
+                value=0,
+            )
+
+            TotalWorkingYears = gr.Slider(
+                label='Total Working Years',
+                minimum=0,
+                maximum=40,
+                step=1,
+                value=8
+            )
+
+            TrainingTimesLastYear = gr.Slider(
+                label='Training Times Last Year',
+                minimum=0,
+                maximum=6,
+                step=1,
+                value=0
+            )
+
+            WorkLifeBalance = gr.Dropdown(
+                label='Work Life balance',
+                choices=['Bad', 'Better', 'Good', 'Best'],
+                multiselect=False,
+                value='Bad',
+            )
+
+            YearsAtCompany = gr.Slider(
+                label='Years At Company',
+                minimum=0,
+                maximum=40,
+                step=1,
+                value=6
+            )
+
+            YearsInCurrentRole = gr.Slider(
+                label='Years In Currentrole',
+                minimum=0,
+                maximum=18,
+                step=1,
+                value=41
+            )
+
+            YearsSinceLastPromotion = gr.Slider(
+                label='Years Since Last Promotion',
+                minimum=0,
+                maximum=15,
+                step=1,
+                value=0
+            )
+
+            YearsWithCurrManager = gr.Slider(
+                label='Years With Curr Manager',
+                minimum=0,
+                maximum=17,
+                step=1,
+                value=5
+            )            
+
+
+
+
+        with gr.Column():
+
+            gr.Markdown(
+                """
+                ## Look if you need some Holy Days 🏝️
+                """
+            )
+
+            label = gr.Label(label="Tipo de Fraude")
+            predict_btn = gr.Button(value="Evaluar")
+            predict_btn.click(
+                predict,
+                inputs=[
+                    Age,
+                    BusinessTravel,
+                    DailyRate,
+                    Department,
+                    DistanceFromHome,
+                    Education,
+                    EducationField,
+                    EnvironmentSatisfaction,
+                    Gender,
+                    HourlyRate,
+                    JobInvolvement,
+                    JobLevel,
+                    JobRole,
+                    JobSatisfaction,
+                    MaritalStatus,
+                    MonthlyIncome,
+                    MonthlyRate,
+                    NumCompaniesWorked,
+                    OverTime,
+                    PercentSalaryHike,
+                    PerformanceRating,
+                    RelationshipSatisfaction,
+                    StockOptionLevel,
+                    TotalWorkingYears,
+                    TrainingTimesLastYear,
+                    WorkLifeBalance,
+                    YearsAtCompany,
+                    YearsInCurrentRole,
+                    YearsSinceLastPromotion,
+                    YearsWithCurrManager,
+                ],
+                outputs=[label],
+                api_name="prediccion"
+            )
+    gr.Markdown(
+        """
+        <p style='text-align: center'>
+            <a href='https://www.escueladedatosvivos.ai/cursos/bootcamp-de-data-science' 
+                target='_blank'>Proyecto demo creado en el bootcamp de EDVAI 🤗
+            </a>
+        </p>
+        <p style='text-align: center'>
+            <a href='https://www.kaggle.com/datasets/pavansubhasht/ibm-hr-analytics-attrition-dataset' 
+                target='_blank'>Data From IBM HR Analytics Employee Attrition & Performance
+            </a>
+        </p>
+        """
+    )
+
+demo.launch()

model/.gitattributes

@@ -0,0 +1 @@
+*.pkl filter=lfs diff=lfs merge=lfs -text

model/model1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8eaa9ffce37733004df1b08b7563f98f645945ac176d760de793c977a91e6c
+size 20202085

requirements.txt

@@ -0,0 +1,183 @@
+aiofiles==23.2.1
+alembic==1.12.0
+altair==5.1.1
+annotated-types==0.5.0
+anyio==3.7.1
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.2.3
+asttokens==2.4.0
+async-lru==2.0.4
+attrs==23.1.0
+Babel==2.12.1
+backcall==0.2.0
+beautifulsoup4==4.12.2
+bleach==6.0.0
+blinker==1.6.2
+certifi==2023.7.22
+cffi==1.15.1
+cfgv==3.4.0
+charset-normalizer==3.2.0
+click==8.1.7
+cloudpickle==2.2.1
+comm==0.1.4
+contourpy==1.1.1
+cycler==0.11.0
+databricks-cli==0.17.8
+dearpygui==1.10.0
+debugpy==1.8.0
+decorator==5.1.1
+defusedxml==0.7.1
+distlib==0.3.7
+docker==6.1.3
+entrypoints==0.4
+exceptiongroup==1.1.3
+executing==1.2.0
+fastapi==0.103.1
+fastjsonschema==2.18.0
+ffmpy==0.3.1
+filelock==3.12.4
+flake8==6.1.0
+Flask==2.3.3
+fonttools==4.42.1
+fqdn==1.5.1
+fsspec==2023.9.1
+funpymodeling==0.1.8
+gfs==1.0.1
+gitdb==4.0.10
+GitPython==3.1.37
+gradio==3.44.4
+gradio_client==0.5.1
+greenlet==2.0.2
+gunicorn==21.2.0
+h11==0.14.0
+httpcore==0.18.0
+httpx==0.25.0
+huggingface-hub==0.17.2
+identify==2.5.29
+idna==3.4
+importlib-metadata==6.8.0
+importlib-resources==6.1.0
+iniconfig==2.0.0
+ipykernel==6.25.2
+ipython==8.15.0
+ipython-genutils==0.2.0
+ipywidgets==8.1.1
+isoduration==20.11.0
+itsdangerous==2.1.2
+jedi==0.19.0
+Jinja2==3.1.2
+joblib==1.3.2
+json5==0.9.14
+jsonpointer==2.4
+jsonschema==4.19.1
+jsonschema-specifications==2023.7.1
+jupyter==1.0.0
+jupyter-console==6.6.3
+jupyter-events==0.7.0
+jupyter-lsp==2.2.0
+jupyter_client==8.3.1
+jupyter_core==5.3.1
+jupyter_server==2.7.3
+jupyter_server_terminals==0.4.4
+jupyterlab==4.0.6
+jupyterlab-pygments==0.2.2
+jupyterlab-widgets==3.0.9
+jupyterlab_server==2.25.0
+kiwisolver==1.4.5
+Mako==1.2.4
+Markdown==3.4.4
+MarkupSafe==2.1.3
+matplotlib==3.8.0
+matplotlib-inline==0.1.6
+mccabe==0.7.0
+mistune==3.0.1
+mlflow==2.7.1
+nbclient==0.8.0
+nbconvert==7.8.0
+nbformat==5.9.2
+nest-asyncio==1.5.8
+nodeenv==1.8.0
+notebook==7.0.4
+notebook_shim==0.2.3
+numpy==1.26.0
+oauthlib==3.2.2
+orjson==3.9.7
+overrides==7.4.0
+packaging==23.1
+pandas==2.1.1
+pandocfilters==1.5.0
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==10.0.1
+platformdirs==3.10.0
+pluggy==1.3.0
+pre-commit==3.4.0
+prometheus-client==0.17.1
+prompt-toolkit==3.0.39
+protobuf==4.24.3
+psutil==5.9.5
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==13.0.0
+pycodestyle==2.11.0
+pycparser==2.21
+pydantic==2.3.0
+pydantic_core==2.6.3
+pydub==0.25.1
+pyflakes==3.1.0
+Pygments==2.16.1
+PyJWT==2.8.0
+pyparsing==3.1.1
+pytest==7.4.2
+python-dateutil==2.8.2
+python-json-logger==2.0.7
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+pyzmq==25.1.1
+qtconsole==5.4.4
+QtPy==2.4.0
+querystring-parser==1.2.4
+referencing==0.30.2
+requests==2.31.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rpds-py==0.10.3
+scikit-learn==1.3.1
+scipy==1.11.2
+seaborn==0.12.2
+semantic-version==2.10.0
+Send2Trash==1.8.2
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+SQLAlchemy==2.0.21
+sqlparse==0.4.4
+stack-data==0.6.2
+starlette==0.27.0
+tabulate==0.9.0
+terminado==0.17.1
+threadpoolctl==3.2.0
+tinycss2==1.2.1
+tomli==2.0.1
+toolz==0.12.0
+tornado==6.3.3
+tqdm==4.66.1
+traitlets==5.10.0
+typing_extensions==4.8.0
+tzdata==2023.3
+uri-template==1.3.0
+urllib3==1.26.16
+uvicorn==0.23.2
+virtualenv==20.24.5
+wcwidth==0.2.6
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.6.3
+websockets==11.0.3
+Werkzeug==2.3.7
+widgetsnbextension==4.0.9
+zipp==3.17.0