| import joblib | |
| import pandas as pd | |
| with open("scaler.joblib", 'rb') as f: | |
| scaler = joblib.load(f) | |
| # data = { | |
| # "Pregnancies": [6], | |
| # "Glucose": [148] | |
| # "BloodPressure": [72], | |
| # "SkinThickness": [35] | |
| # "BMI": [33.6], | |
| # "DiabetesPedigreeFunction": [0.627] | |
| # "Age": [50] | |
| # } | |
| # df = pd.DataFrame(data) | |
| outs = scaler.transform([[6, 148, 72, 35, 33.6, 0.627, 50]]) | |
| for i in outs[0]: | |
| print(i) | |
| # def is_number(text): | |
| # try: | |
| # # Try to convert the text to a float | |
| # float(text) | |
| # return True | |
| # except ValueError: | |
| # # If conversion fails, it's not a number | |
| # return False | |
| # inp = "1.5" | |
| # if is_number(inp): | |
| # print(int(inp.split('.')[0])) | |
| # print(int(1.5)) | |
| # def diabetic_pedigree_function(mother, father, siblings): | |
| # """ | |
| # Calculate a scaled Diabetic Pedigree Function (DPF) for an individual, | |
| # aiming for an output range of approximately (0.078, 2.42). | |
| # Parameters: | |
| # mother (int): 1 if the mother has diabetes, 0 otherwise. | |
| # father (int): 1 if the father has diabetes, 0 otherwise. | |
| # siblings (list): A list of 0s and 1s representing siblings' diabetes status. | |
| # Returns: | |
| # float: The scaled diabetic pedigree function score. | |
| # """ | |
| # # Assign weights to each family member | |
| # mother_weight = 0.5 | |
| # father_weight = 0.5 | |
| # sibling_weight = 0.25 | |
| # # Calculate the weighted contributions | |
| # family_history = (mother * mother_weight) + (father * father_weight) + (sum(siblings) * sibling_weight) | |
| # # Add a scaling factor to shift the range | |
| # scaling_factor = 1.2 | |
| # bias = 0.078 # Minimum value in the desired range | |
| # # Final scaled DPF score | |
| # dpf_score = family_history * scaling_factor + bias | |
| # return round(dpf_score, 3) # Rounded for clarity | |
| # # Example usage: | |
| # mother_history = 1 # Mother has diabetes | |
| # father_history = 0 # Father doesn't have diabetes | |
| # siblings_history = [1, 0, 0] # One sibling has diabetes, two do not | |
| # dpf = diabetic_pedigree_function(mother_history, father_history, siblings_history) | |
| # print(f"The Diabetic Pedigree Function score is: {dpf}") | |