Upload app.py

app.py

@@ -3,65 +3,190 @@ import hopsworks
 import joblib
 import pandas as pd
 
-features = ['fixed_acidity',
-            'volatile_acidity',
-            'citric_acid',
-            'residual_sugar',
-            'chlorides',
-            'free_sulfur_dioxide',
-            'total_sulfur_dioxide',
-            'density',
-            'pH',
-            'sulphates',
-            'alcohol',
-            'is_white']
-labels = ["Low", "Medium", "High"]
+features =  ['work_year',
+             'experience_level',
+             'company_size',
+             'eur',
+             'gbp',
+             'usd',
+             'engineer',
+             'scientist',
+             'research',
+             'analyst',
+             'analytics_engineer',
+             'applied_scientist',
+             'bi_developer',
+             'business_intelligence_analyst',
+             'business_intelligence_engineer',
+             'data_analyst',
+             'data_architect',
+             'data_engineer',
+             'data_manager',
+             'data_science_consultant',
+             'data_science_manager',
+             'data_scientist',
+             'ml_engineer',
+             'machine_learning_engineer',
+             'machine_learning_scientist',
+             'research_analyst',
+             'research_engineer',
+             'research_scientist',
+             'gdp',
+             'cpi']
+
+
+labels = ['(16454.999, 122000.0]', '(122000.0, 170000.0]', '(170000.0, 329700.0]']
 
 project = hopsworks.login()
 fs = project.get_feature_store()
 
 mr = project.get_model_registry()
-model = mr.get_model("wine_model", version=1)
+model = mr.get_model("salary_model", version=4)
 model_dir = model.download()
-model = joblib.load(model_dir + "/wine_model.pkl")
+model = joblib.load(model_dir + "/model.pkl")
 print("Model downloaded")
 
+import requests
+
+def get_gdp_by_country_code(country_code, year=2023, index='FP.CPI.TOTL'):
+    # World Bank API endpoint for GDP data
+    api_url = f'http://api.worldbank.org/v2/country/{country_code}/indicator/{index}?data={year}&format=json'
+
+
+    # Make a GET request to the API
+    response = requests.get(api_url)
+
+    # Check if the request was successful (status code 200)
+    if response.status_code == 200:
+        # Parse the JSON response
+        data = response.json()
+
+        # Extract the GDP value from the response
+        gdp_value = data[1][0]['value'] if data[1] else None
+
+        return gdp_value
+    else:
+        # If the request was not successful, print an error message
+        print(f"Error: Unable to fetch data. Status code: {response.status_code}")
+        return None
+
+def salary(work_year,
+             experience_level,
+             company_size,
+             currency,
+             job_title,
+             country)-> str:
+
+    other_param = {}
+
+    other_param['gdp'] = get_gdp_by_country_code(country, work_year, 'NY.GDP.MKTP.CD')
+    other_param['cpi'] = get_gdp_by_country_code(country, work_year, 'FP.CPI.TOTL')
+
+    jobs =   ['analytics_engineer',
+             'applied_scientist',
+             'bi_developer',
+             'business_intelligence_analyst',
+             'business_intelligence_engineer',
+             'data_analyst',
+             'data_architect',
+             'data_engineer',
+             'data_manager',
+             'data_science_consultant',
+             'data_science_manager',
+             'data_scientist',
+             'ml_engineer',
+             'machine_learning_engineer',
+             'machine_learning_scientist',
+             'research_analyst',
+             'research_engineer',
+             'research_scientist']
+
+    jobs_flag ={}
+
+    for name in jobs:
+        if name == job_title.lower().replace(' ', '_'):
+            jobs_flag[name] = True
+        else:
+            jobs_flag[name] = False
 
-def wine(fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, free_sulfur_dioxide,
-         total_sulfur_dioxide, density, pH, sulphates, alcohol, white) -> str:
-    print("Calling function")
-    df = pd.DataFrame([[fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, free_sulfur_dioxide,
-         total_sulfur_dioxide, density, pH, sulphates, alcohol, white]], columns=features)
+    role = [
+        'engineer',
+        'scientist',
+        'research',
+        'analyst'
+    ]
+
+    role_flag = {}
+
+    for name in role:
+        if role in job_title.lower():
+            role_flag[name]= True
+        else:
+            role_flag[name] = False
+
+    currency_flag = {
+        'eur': False,
+        'gbp': False,
+        'usd': False
+    }
+
+    currency_flag[currency.lower()] = True
+
+    company_size_dic = {
+        'S': 0,
+        'M': 1,
+        'L': 2,
+    }
+
+    other_param['company_size'] = company_size_dic[company_size]
+
+    experience_level_map = {
+        'EN': 0,
+        'MI': 1,
+        'SE': 2,
+        'EX': 3
+    }
+
+    other_param['experience_level'] = experience_level_map[experience_level]
+
+    params = {}
+
+    params.update(other_param)
+    params.update(jobs_flag)
+    params.update(currency_flag)
+    params.update(role_flag)
+
+
+    df = pd.DataFrame(params)
     print("Predicting")
     print(df)
-    # 'res' is a list of predictions returned as the label.
+
     res = model.predict(df)
-    # We add '[0]' to the result of the transformed 'res', because 'res' is a list, and we only want
-    # the first element.
-    #     print("Res: {0}").format(res)
-    print(res)
 
-    return f"{labels[res[0]]} quality"
+    print(f"{labels[res[0]]} $")
+    return f"{labels[res[0]]} $"
 
+job_title_options = [
+        'Analytics Engineer', 'Applied Scientist', 'BI Developer',
+        'Business Intelligence Analyst', 'Business Intelligence Engineer',
+        'Data Analyst', 'Data Architect', 'Data Engineer', 'Data Manager',
+        'Data Science Consultant', 'Data Science Manager', 'Data Scientist',
+        'ML Engineer', 'Machine Learning Engineer', 'Machine Learning Scientist',
+        'Research Analyst', 'Research Engineer', 'Research Scientist'
+    ]
 
 demo = gr.Interface(
-    fn=wine,
-    title="Wine Quality Predictive Analytics",
-    description="Experiment with wine characteristics to get the wine quality (low, medium, high)",
+    fn=salary,
+    title="Salary prediction",
+    description="Prediction of the salary in USD",
     allow_flagging="never",
     inputs=[
-        gr.components.Number(label='fixed acidity'),
-        gr.components.Number(label='volatile acidity'),
-        gr.components.Number(label='citric acid'),
-        gr.components.Number(label='residual sugar'),
-        gr.components.Number(label='chlorides'),
-        gr.components.Number(label='free sulfur dioxide'),
-        gr.components.Number(label='total sulfur dioxide'),
-        gr.components.Number(label='density'),
-        gr.components.Number(label='pH'),
-        gr.components.Number(label='sulphates'),
-        gr.components.Number(label='alcohol'),
-        gr.components.Checkbox(label='is white'),
+        gr.components.Number(label='Work Year', bind='work_year'),
+        gr.components.Select(label='Experience Level', options=['EN', 'MI', 'SE', 'EX'], bind='experience_level'),
+        gr.components.Select(label='Company Size', options=['S', 'M', 'L'], bind='company_size'),
+        gr.components.Select(label='Currency', options=['EUR', 'GBP', 'USD'], bind='currency'),
+        gr.components.Select(label='Job Title', options=job_title_options, bind='job_title'),
+        gr.components.TextInput(label='Country (3 letter code)', bind='country')
     ],
     outputs=gr.Text())