├── Small_examples └── init ├── docker_deploy ├── app │ ├── __init__.py │ ├── requirements.txt │ ├── aditya_model1_adaboost.joblib │ ├── __pycache__ │ │ ├── main.cpython-37.pyc │ │ ├── utils.cpython-37.pyc │ │ ├── constants.cpython-37.pyc │ │ └── data_model.cpython-37.pyc │ ├── data_model.py │ ├── constants.py │ ├── utils.py │ └── main.py ├── requirements.txt └── Dockerfile ├── unit testing ├── unit_test │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-37.pyc │ │ ├── test_encode_features.cpython-37-pytest-5.4.3.pyc │ │ ├── test_normalize_data.cpython-37-pytest-5.4.3.pyc │ │ ├── test_get_inference_data.cpython-37-pytest-5.4.3.pyc │ │ ├── test_apply_pre_proceesing.cpython-37-pytest-5.4.3.pyc │ │ └── test_apply_pre_processing.cpython-37-pytest-5.4.3.pyc │ ├── test_encode_features.py │ ├── test_apply_pre_proceesing.py │ ├── test_normalize_data.py │ └── test_get_inference_data.py ├── pytest_command.txt ├── aditya_model2_svm.joblib ├── aditya_model1_adaboost.joblib ├── __pycache__ │ ├── main.cpython-37.pyc │ ├── utils.cpython-37.pyc │ └── constants.cpython-37.pyc ├── data_model.py ├── Data │ ├── inference_heart_disease.csv │ └── heart.csv ├── constants.py ├── utils.py ├── Heart Disease Inference Modularized.ipynb └── main.py ├── exception handling and logging ├── __init__.py ├── unit_test │ ├── __init__.py │ ├── test_encode_features.py │ ├── test_apply_pre_proceesing.py │ ├── test_get_inference_data.py │ └── test_normalize_data.py ├── aditya_model2_svm.joblib ├── aditya_model1_adaboost.joblib ├── __pycache__ │ ├── utils.cpython-37.pyc │ └── constants.cpython-37.pyc ├── data_model.py ├── Data │ ├── inference_heart_disease.csv │ └── heart.csv ├── constants.py ├── inference_pipe_exec.log ├── main.py ├── utils.py ├── Heart Disease Inference Modularized.ipynb └── main_old.py ├── docker_commands.docx ├── docker_commands.pdf ├── python scripting ├── aditya_model2_svm.joblib ├── aditya_model1_adaboost.pkl ├── aditya_model1_adaboost.joblib ├── __pycache__ │ ├── utils.cpython-37.pyc │ └── constants.cpython-37.pyc ├── data_model.py ├── Data │ ├── inference_heart_disease.csv │ └── heart.csv ├── constants.py ├── main.py ├── utils.py ├── Heart Disease Inference Modularized.ipynb └── Heart Disease Inference.py ├── uci_heart_disease ├── aditya_model2_svm.joblib ├── aditya_model1_adaboost.pkl ├── aditya_model1_adaboost.joblib ├── __pycache__ │ ├── utils.cpython-37.pyc │ └── constants.cpython-37.pyc ├── constants.py ├── data_model.py ├── Data │ ├── inference_heart_disease.csv │ └── heart.csv ├── utils.py ├── main.py ├── Heart Disease Inference.py ├── Heart Disease Inference Modularized.ipynb └── Heart Disease Inference.ipynb ├── code linting ├── commands_pycodestyle.txt ├── Corrected │ ├── utils.py │ └── Heart Disease Inference.py ├── utils.py └── Heart Disease Inference.py ├── code documentation ├── commands_pycodestyle.txt ├── constants.py ├── Corrected │ ├── constants.py │ ├── utils.py │ ├── Heart Disease Inference Modularized.ipynb │ └── Heart Disease Inference.py ├── utils.py ├── Heart Disease Inference.py └── Heart Disease Inference Modularized.ipynb ├── Links.txt ├── fast api └── HelloWorldFAPI.py ├── env create.txt ├── docker_commands.txt └── requirements.txt /Small_examples/init: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /docker_deploy/app/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /unit testing/unit_test/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /exception handling and logging/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /exception handling and logging/unit_test/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /docker_commands.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/docker_commands.docx -------------------------------------------------------------------------------- /docker_commands.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/docker_commands.pdf -------------------------------------------------------------------------------- /unit testing/pytest_command.txt: -------------------------------------------------------------------------------- 1 | $pytest -q 2 | $pytest -q unit_test\test_get_inference_data.py 3 | $tree /f # to view directory structure -------------------------------------------------------------------------------- /unit testing/aditya_model2_svm.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/aditya_model2_svm.joblib -------------------------------------------------------------------------------- /docker_deploy/app/requirements.txt: -------------------------------------------------------------------------------- 1 | fastapi 2 | matplotlib 3 | numpy 4 | pandas 5 | pydantic 6 | scikit-learn 7 | scipy 8 | seaborn 9 | uvicorn[standard] -------------------------------------------------------------------------------- /docker_deploy/requirements.txt: -------------------------------------------------------------------------------- 1 | fastapi 2 | matplotlib 3 | numpy 4 | pandas 5 | pydantic 6 | scikit-learn 7 | scipy 8 | seaborn 9 | "uvicorn[standard]" -------------------------------------------------------------------------------- /python scripting/aditya_model2_svm.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/python scripting/aditya_model2_svm.joblib -------------------------------------------------------------------------------- /python scripting/aditya_model1_adaboost.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/python scripting/aditya_model1_adaboost.pkl -------------------------------------------------------------------------------- /uci_heart_disease/aditya_model2_svm.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/uci_heart_disease/aditya_model2_svm.joblib -------------------------------------------------------------------------------- /unit testing/aditya_model1_adaboost.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/aditya_model1_adaboost.joblib -------------------------------------------------------------------------------- /python scripting/aditya_model1_adaboost.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/python scripting/aditya_model1_adaboost.joblib -------------------------------------------------------------------------------- /uci_heart_disease/aditya_model1_adaboost.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/uci_heart_disease/aditya_model1_adaboost.pkl -------------------------------------------------------------------------------- /unit testing/__pycache__/main.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/__pycache__/main.cpython-37.pyc -------------------------------------------------------------------------------- /unit testing/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /docker_deploy/app/aditya_model1_adaboost.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/docker_deploy/app/aditya_model1_adaboost.joblib -------------------------------------------------------------------------------- /uci_heart_disease/aditya_model1_adaboost.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/uci_heart_disease/aditya_model1_adaboost.joblib -------------------------------------------------------------------------------- /code linting/commands_pycodestyle.txt: -------------------------------------------------------------------------------- 1 | pycodestyle --first file_name.py 2 | pycodestyle --show-source --show-pep8 file_name.py 3 | pycodestyle --statistics -qq file_name.py -------------------------------------------------------------------------------- /docker_deploy/app/__pycache__/main.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/docker_deploy/app/__pycache__/main.cpython-37.pyc -------------------------------------------------------------------------------- /docker_deploy/app/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/docker_deploy/app/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /python scripting/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/python scripting/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /uci_heart_disease/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/uci_heart_disease/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /unit testing/__pycache__/constants.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/__pycache__/constants.cpython-37.pyc -------------------------------------------------------------------------------- /code documentation/commands_pycodestyle.txt: -------------------------------------------------------------------------------- 1 | pycodestyle --first file_name.py 2 | pycodestyle --show-source --show-pep8 file_name.py 3 | pycodestyle --statistics -qq file_name.py -------------------------------------------------------------------------------- /python scripting/__pycache__/constants.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/python scripting/__pycache__/constants.cpython-37.pyc -------------------------------------------------------------------------------- /docker_deploy/app/__pycache__/constants.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/docker_deploy/app/__pycache__/constants.cpython-37.pyc -------------------------------------------------------------------------------- /docker_deploy/app/__pycache__/data_model.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/docker_deploy/app/__pycache__/data_model.cpython-37.pyc -------------------------------------------------------------------------------- /exception handling and logging/aditya_model2_svm.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/exception handling and logging/aditya_model2_svm.joblib -------------------------------------------------------------------------------- /uci_heart_disease/__pycache__/constants.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/uci_heart_disease/__pycache__/constants.cpython-37.pyc -------------------------------------------------------------------------------- /unit testing/unit_test/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/unit_test/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /exception handling and logging/aditya_model1_adaboost.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/exception handling and logging/aditya_model1_adaboost.joblib -------------------------------------------------------------------------------- /exception handling and logging/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/exception handling and logging/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /exception handling and logging/__pycache__/constants.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/exception handling and logging/__pycache__/constants.cpython-37.pyc -------------------------------------------------------------------------------- /unit testing/unit_test/__pycache__/test_encode_features.cpython-37-pytest-5.4.3.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/unit_test/__pycache__/test_encode_features.cpython-37-pytest-5.4.3.pyc -------------------------------------------------------------------------------- /unit testing/unit_test/__pycache__/test_normalize_data.cpython-37-pytest-5.4.3.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/unit_test/__pycache__/test_normalize_data.cpython-37-pytest-5.4.3.pyc -------------------------------------------------------------------------------- /unit testing/unit_test/__pycache__/test_get_inference_data.cpython-37-pytest-5.4.3.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/unit_test/__pycache__/test_get_inference_data.cpython-37-pytest-5.4.3.pyc -------------------------------------------------------------------------------- /docker_deploy/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM python:3.7.7 2 | 3 | COPY ./app /app 4 | 5 | WORKDIR /app 6 | 7 | RUN pip install -r requirements.txt 8 | 9 | EXPOSE 8000 10 | 11 | ENTRYPOINT ["uvicorn"] 12 | 13 | CMD ["main:app", "--host", "0.0.0.0"] -------------------------------------------------------------------------------- /unit testing/unit_test/__pycache__/test_apply_pre_proceesing.cpython-37-pytest-5.4.3.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/unit_test/__pycache__/test_apply_pre_proceesing.cpython-37-pytest-5.4.3.pyc -------------------------------------------------------------------------------- /unit testing/unit_test/__pycache__/test_apply_pre_processing.cpython-37-pytest-5.4.3.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ContentUpgrad/Pre-Requisite_MLOps/master/unit testing/unit_test/__pycache__/test_apply_pre_processing.cpython-37-pytest-5.4.3.pyc -------------------------------------------------------------------------------- /Links.txt: -------------------------------------------------------------------------------- 1 | https://towardsdatascience.com/how-you-can-quickly-deploy-your-ml-models-with-fastapi-9428085a87bf 2 | https://towardsdatascience.com/how-to-deploy-a-machine-learning-model-with-fastapi-docker-and-github-actions-13374cbd638a 3 | https://hub.docker.com/_/hello-world 4 | https://docs.docker.com/desktop/ -------------------------------------------------------------------------------- /fast api/HelloWorldFAPI.py: -------------------------------------------------------------------------------- 1 | # !pip install fastapi 2 | # !pip install "uvicorn[standard]" 3 | import uvicorn 4 | from fastapi import FastAPI 5 | 6 | app = FastAPI() 7 | 8 | @app.get("/") 9 | def home(): 10 | return {"Hello" : "World"} 11 | 12 | if __name__ == "__main__": 13 | uvicorn.run("HelloWorldFAPI:app") -------------------------------------------------------------------------------- /unit testing/unit_test/test_encode_features.py: -------------------------------------------------------------------------------- 1 | # 1. Write test case to validate if length of 2 | # ONE_HOT_ENCODED_FEATURES list is matching the 3 | # number of columns of the 4 | # input dataframe to encode_features() 5 | 6 | 7 | # 2. Write a test case to ensure all 8 | # categorical values are converted to 9 | # vector encodings -------------------------------------------------------------------------------- /exception handling and logging/unit_test/test_encode_features.py: -------------------------------------------------------------------------------- 1 | # 1. Write test case to validate if length of 2 | # ONE_HOT_ENCODED_FEATURES list is matching the 3 | # number of columns of the 4 | # input dataframe to encode_features() 5 | 6 | 7 | # 2. Write a test case to ensure all 8 | # categorical values are converted to 9 | # vector encodings -------------------------------------------------------------------------------- /unit testing/unit_test/test_apply_pre_proceesing.py: -------------------------------------------------------------------------------- 1 | # 1. Write a test case to check 2 | # if the FEATURES_TO_ENCODE constant 3 | # is not coming as null and 4 | # all the list elements are 5 | # string in data type 6 | 7 | 8 | # 2. Write a test case to ensure that the shape of the 9 | # dataframes are consistent after one hot encoding 10 | # and data normlization -------------------------------------------------------------------------------- /exception handling and logging/unit_test/test_apply_pre_proceesing.py: -------------------------------------------------------------------------------- 1 | # 1. Write a test case to check 2 | # if the FEATURES_TO_ENCODE constant 3 | # is not coming as null and 4 | # all the list elements are 5 | # string in data type 6 | 7 | 8 | # 2. Write a test case to ensure that the shape of the 9 | # dataframes are consistent after one hot encoding 10 | # and data normlization -------------------------------------------------------------------------------- /unit testing/unit_test/test_normalize_data.py: -------------------------------------------------------------------------------- 1 | import warnings 2 | warnings.filterwarnings("ignore") 3 | from utils import * 4 | import pandas as pd 5 | 6 | class TestDataNormalization: 7 | def test_norm_data_len(self): 8 | inference_data, labels = get_inference_data() 9 | norm_df = normalize_data(inference_data) 10 | assert len(inference_data) == len(norm_df), "length has changed after normalization" -------------------------------------------------------------------------------- /unit testing/data_model.py: -------------------------------------------------------------------------------- 1 | from pydantic import BaseModel 2 | from typing import Optional 3 | 4 | class InputDataModel(BaseModel): 5 | age: float 6 | sex: int 7 | chest_pain_type: int 8 | resting_bp: float 9 | cholestoral: float 10 | fasting_blood_sugar: float 11 | restecg: int 12 | max_hr: float 13 | exang: int 14 | oldpeak: float 15 | slope: int 16 | num_major_vessels: int 17 | thal: int 18 | 19 | class OutputDataModel(BaseModel): 20 | predicted_value: bool 21 | predicted_class: str 22 | -------------------------------------------------------------------------------- /docker_deploy/app/data_model.py: -------------------------------------------------------------------------------- 1 | from pydantic import BaseModel 2 | from typing import Optional 3 | 4 | class InputDataModel(BaseModel): 5 | age: float 6 | sex: int 7 | chest_pain_type: int 8 | resting_bp: float 9 | cholestoral: float 10 | fasting_blood_sugar: float 11 | restecg: int 12 | max_hr: float 13 | exang: int 14 | oldpeak: float 15 | slope: int 16 | num_major_vessels: int 17 | thal: int 18 | 19 | class OutputDataModel(BaseModel): 20 | predicted_value: bool 21 | predicted_class: str 22 | -------------------------------------------------------------------------------- /python scripting/data_model.py: -------------------------------------------------------------------------------- 1 | from pydantic import BaseModel 2 | from typing import Optional 3 | 4 | class InputDataModel(BaseModel): 5 | age: float 6 | sex: int 7 | chest_pain_type: int 8 | resting_bp: float 9 | cholestoral: float 10 | fasting_blood_sugar: float 11 | restecg: int 12 | max_hr: float 13 | exang: int 14 | oldpeak: float 15 | slope: int 16 | num_major_vessels: int 17 | thal: int 18 | 19 | class OutputDataModel(BaseModel): 20 | predicted_value: bool 21 | predicted_class: str 22 | -------------------------------------------------------------------------------- /exception handling and logging/data_model.py: -------------------------------------------------------------------------------- 1 | from pydantic import BaseModel 2 | from typing import Optional 3 | 4 | class InputDataModel(BaseModel): 5 | age: float 6 | sex: int 7 | chest_pain_type: int 8 | resting_bp: float 9 | cholestoral: float 10 | fasting_blood_sugar: float 11 | restecg: int 12 | max_hr: float 13 | exang: int 14 | oldpeak: float 15 | slope: int 16 | num_major_vessels: int 17 | thal: int 18 | 19 | class OutputDataModel(BaseModel): 20 | predicted_value: bool 21 | predicted_class: str 22 | -------------------------------------------------------------------------------- /uci_heart_disease/constants.py: -------------------------------------------------------------------------------- 1 | ONE_HOT_ENCODED_FEATURES = ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 2 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 3 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 4 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 5 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'] 6 | 7 | FEATURES_TO_ENCODE = ['thal', 'slope', 'chest_pain_type', 'restecg'] 8 | 9 | MODEL_NAME = 'aditya_model1_adaboost.joblib' 10 | -------------------------------------------------------------------------------- /uci_heart_disease/data_model.py: -------------------------------------------------------------------------------- 1 | from pydantic import BaseModel 2 | from typing import Optional 3 | 4 | class InputDataModel(BaseModel): 5 | age: float 6 | sex: int 7 | chest_pain_type: int 8 | resting_bp: float 9 | cholestoral: float 10 | fasting_blood_sugar: float 11 | restecg: int 12 | max_hr: float 13 | exang: int 14 | oldpeak: float 15 | slope: int 16 | num_major_vessels: int 17 | thal: int 18 | 19 | class OutputDataModel(BaseModel): 20 | predicted_value: bool 21 | predicted_class: str 22 | -------------------------------------------------------------------------------- /unit testing/unit_test/test_get_inference_data.py: -------------------------------------------------------------------------------- 1 | import warnings 2 | warnings.filterwarnings("ignore") 3 | from utils import * 4 | import pandas as pd 5 | 6 | 7 | class TestGetInferenceData: 8 | def test_method_output_type(self): 9 | df = pd.DataFrame() 10 | inference_data, labels = get_inference_data() 11 | assert type(inference_data)==type(df), "inference data should be a dataframe" 12 | 13 | def test_method_output_len(self): 14 | inference_data, labels = get_inference_data() 15 | assert len(inference_data) == len(labels), "length of data and labels are not matching" -------------------------------------------------------------------------------- /exception handling and logging/unit_test/test_get_inference_data.py: -------------------------------------------------------------------------------- 1 | import warnings 2 | warnings.filterwarnings("ignore") 3 | from utils import * 4 | import pandas as pd 5 | 6 | 7 | class TestGetInferenceData: 8 | def test_method_output_type(self): 9 | df = pd.DataFrame() 10 | inference_data, labels = get_inference_data() 11 | assert type(inference_data)==type(df), "inference data should be a dataframe" 12 | 13 | def test_method_output_len(self): 14 | inference_data, labels = get_inference_data() 15 | assert len(inference_data) == len(labels), "length of data and labels are not matching" -------------------------------------------------------------------------------- /docker_deploy/app/constants.py: -------------------------------------------------------------------------------- 1 | MODEL_NAME = 'aditya_model1_adaboost.joblib' 2 | ORIGINAL_FEATURES = ['age', 'sex', 'chest_pain_type', 'resting_bp', 'cholestoral', 3 | 'fasting_blood_sugar', 'restecg', 'max_hr', 'exang', 'oldpeak', 'slope', 4 | 'num_major_vessels', 'thal'] 5 | FEATURES_TO_ENCODE = ['thal', 'slope', 'chest_pain_type', 'restecg'] 6 | ONE_HOT_ENCODED_FEATURES = ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 7 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 8 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 9 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 10 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'] -------------------------------------------------------------------------------- /code documentation/constants.py: -------------------------------------------------------------------------------- 1 | MODEL_NAME = 'aditya_model1_adaboost.joblib' 2 | ORIGINAL_FEATURES = ['age', 'sex', 'chest_pain_type', 'resting_bp', 'cholestoral', 3 | 'fasting_blood_sugar', 'restecg', 'max_hr', 'exang', 'oldpeak', 'slope', 4 | 'num_major_vessels', 'thal'] 5 | FEATURES_TO_ENCODE = ['thal', 'slope', 'chest_pain_type', 'restecg'] 6 | ONE_HOT_ENCODED_FEATURES = ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 7 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 8 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 9 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 10 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'] 11 | -------------------------------------------------------------------------------- /env create.txt: -------------------------------------------------------------------------------- 1 | python -m venv deployment/ # create environment 2 | deployment\Scripts\activate.bat # activate environment 3 | deactivate # deactivate environment 4 | pip freeze > requirements.txt # Requirement.txt 5 | cat requirements.txt # Requirement.txt 6 | 7 | 8 | # Post Call Body 9 | { 10 | "age": 66, 11 | "sex": 1, 12 | "chest_pain_type": 0, 13 | "resting_bp": 120, 14 | "cholestoral": 302, 15 | "fasting_blood_sugar": 0, 16 | "restecg": 0, 17 | "max_hr": 151, 18 | "exang": 0, 19 | "oldpeak": 0.4, 20 | "slope": 1, 21 | "num_major_vessels": 0, 22 | "thal": 2 23 | } 24 | 25 | ============= 26 | Environment Variable 27 | DOCKER_HOST 28 | tcp://192.168.99.100:2376 29 | tcp://localhost:2375 30 | DOCKER_TLS_VERIFY 31 | 1 -------------------------------------------------------------------------------- /exception handling and logging/unit_test/test_normalize_data.py: -------------------------------------------------------------------------------- 1 | ''' 2 | import warnings 3 | warnings.filterwarnings("ignore") 4 | from utils import * 5 | import pandas as pd 6 | 7 | 8 | class TestDataNormalization: 9 | def test_norm_data_len(self): 10 | inference_data, labels = get_inference_data() 11 | norm_df = normalize_data(inference_data) 12 | assert len(inference_data)==len(norm_df),"Length has changed after normalization" 13 | 14 | def test_norm_data_valuerange(self): 15 | inference_data, labels = get_inference_data() 16 | norm_df = normalize_data(inference_data) 17 | assert int(norm_df.max().max()) <= 1,"Max value after normalization should be 1" 18 | assert int(norm_df.min().min()) >= 0,"Min value after normalization should be 0" 19 | ''' -------------------------------------------------------------------------------- /unit testing/Data/inference_heart_disease.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 3 | 52,1,0,112,230,0,1,160,0,0.0,2,1,2,0 4 | 63,0,1,140,195,0,1,179,0,0.0,2,2,2,1 5 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 6 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 7 | 41,1,2,130,214,0,0,168,0,2.0,1,0,2,1 8 | 39,0,2,94,199,0,1,179,0,0.0,2,0,2,1 9 | 48,1,0,130,256,1,0,150,1,0.0,2,2,3,0 10 | 57,1,0,110,335,0,1,143,1,3.0,1,1,3,0 11 | 47,1,2,138,257,0,0,156,0,0.0,2,0,2,1 12 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 13 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 14 | 53,1,0,142,226,0,0,111,1,0.0,2,0,3,1 15 | 41,1,1,120,157,0,1,182,0,0.0,2,0,2,1 16 | 54,1,0,110,206,0,0,108,1,0.0,1,1,2,0 17 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 18 | 42,1,0,140,226,0,1,178,0,0.0,2,0,2,1 19 | 29,1,1,130,204,0,0,202,0,0.0,2,0,2,1 20 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 21 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 22 | -------------------------------------------------------------------------------- /python scripting/Data/inference_heart_disease.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 3 | 52,1,0,112,230,0,1,160,0,0.0,2,1,2,0 4 | 63,0,1,140,195,0,1,179,0,0.0,2,2,2,1 5 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 6 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 7 | 41,1,2,130,214,0,0,168,0,2.0,1,0,2,1 8 | 39,0,2,94,199,0,1,179,0,0.0,2,0,2,1 9 | 48,1,0,130,256,1,0,150,1,0.0,2,2,3,0 10 | 57,1,0,110,335,0,1,143,1,3.0,1,1,3,0 11 | 47,1,2,138,257,0,0,156,0,0.0,2,0,2,1 12 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 13 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 14 | 53,1,0,142,226,0,0,111,1,0.0,2,0,3,1 15 | 41,1,1,120,157,0,1,182,0,0.0,2,0,2,1 16 | 54,1,0,110,206,0,0,108,1,0.0,1,1,2,0 17 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 18 | 42,1,0,140,226,0,1,178,0,0.0,2,0,2,1 19 | 29,1,1,130,204,0,0,202,0,0.0,2,0,2,1 20 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 21 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 22 | -------------------------------------------------------------------------------- /uci_heart_disease/Data/inference_heart_disease.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 3 | 52,1,0,112,230,0,1,160,0,0.0,2,1,2,0 4 | 63,0,1,140,195,0,1,179,0,0.0,2,2,2,1 5 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 6 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 7 | 41,1,2,130,214,0,0,168,0,2.0,1,0,2,1 8 | 39,0,2,94,199,0,1,179,0,0.0,2,0,2,1 9 | 48,1,0,130,256,1,0,150,1,0.0,2,2,3,0 10 | 57,1,0,110,335,0,1,143,1,3.0,1,1,3,0 11 | 47,1,2,138,257,0,0,156,0,0.0,2,0,2,1 12 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 13 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 14 | 53,1,0,142,226,0,0,111,1,0.0,2,0,3,1 15 | 41,1,1,120,157,0,1,182,0,0.0,2,0,2,1 16 | 54,1,0,110,206,0,0,108,1,0.0,1,1,2,0 17 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 18 | 42,1,0,140,226,0,1,178,0,0.0,2,0,2,1 19 | 29,1,1,130,204,0,0,202,0,0.0,2,0,2,1 20 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 21 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 22 | -------------------------------------------------------------------------------- /exception handling and logging/Data/inference_heart_disease.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 3 | 52,1,0,112,230,0,1,160,0,0.0,2,1,2,0 4 | 63,0,1,140,195,0,1,179,0,0.0,2,2,2,1 5 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 6 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 7 | 41,1,2,130,214,0,0,168,0,2.0,1,0,2,1 8 | 39,0,2,94,199,0,1,179,0,0.0,2,0,2,1 9 | 48,1,0,130,256,1,0,150,1,0.0,2,2,3,0 10 | 57,1,0,110,335,0,1,143,1,3.0,1,1,3,0 11 | 47,1,2,138,257,0,0,156,0,0.0,2,0,2,1 12 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 13 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 14 | 53,1,0,142,226,0,0,111,1,0.0,2,0,3,1 15 | 41,1,1,120,157,0,1,182,0,0.0,2,0,2,1 16 | 54,1,0,110,206,0,0,108,1,0.0,1,1,2,0 17 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 18 | 42,1,0,140,226,0,1,178,0,0.0,2,0,2,1 19 | 29,1,1,130,204,0,0,202,0,0.0,2,0,2,1 20 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 21 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 22 | -------------------------------------------------------------------------------- /unit testing/constants.py: -------------------------------------------------------------------------------- 1 | ''' 2 | constants.py contains all variables 3 | where constant values are assigned 4 | ''' 5 | 6 | # Latest model to be used in the inference process 7 | MODEL_NAME = 'aditya_model1_adaboost.joblib' 8 | # Column names of the source tabular data 9 | ORIGINAL_FEATURES = ['age', 'sex', 'chest_pain_type', 'resting_bp', 'cholestoral', 10 | 'fasting_blood_sugar', 'restecg', 'max_hr', 'exang', 'oldpeak', 'slope', 11 | 'num_major_vessels', 'thal'] 12 | # Categorical features that needs to be one hot encoded 13 | FEATURES_TO_ENCODE = ['thal', 'slope', 'chest_pain_type', 'restecg'] 14 | # Feature names after one hot encoding 15 | ONE_HOT_ENCODED_FEATURES = ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 16 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 17 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 18 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 19 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'] 20 | -------------------------------------------------------------------------------- /python scripting/constants.py: -------------------------------------------------------------------------------- 1 | ''' 2 | constants.py contains all variables 3 | where constant values are assigned 4 | ''' 5 | 6 | # Latest model to be used in the inference process 7 | MODEL_NAME = 'aditya_model1_adaboost.joblib' 8 | # Column names of the source tabular data 9 | ORIGINAL_FEATURES = ['age', 'sex', 'chest_pain_type', 'resting_bp', 'cholestoral', 10 | 'fasting_blood_sugar', 'restecg', 'max_hr', 'exang', 'oldpeak', 'slope', 11 | 'num_major_vessels', 'thal'] 12 | # Categorical features that needs to be one hot encoded 13 | FEATURES_TO_ENCODE = ['thal', 'slope', 'chest_pain_type', 'restecg'] 14 | # Feature names after one hot encoding 15 | ONE_HOT_ENCODED_FEATURES = ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 16 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 17 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 18 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 19 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'] 20 | -------------------------------------------------------------------------------- /code documentation/Corrected/constants.py: -------------------------------------------------------------------------------- 1 | ''' 2 | constants.py contains all variables 3 | where constant values are assigned 4 | ''' 5 | 6 | # Latest model to be used in the inference process 7 | MODEL_NAME = 'aditya_model1_adaboost.joblib' 8 | # Column names of the source tabular data 9 | ORIGINAL_FEATURES = ['age', 'sex', 'chest_pain_type', 'resting_bp', 'cholestoral', 10 | 'fasting_blood_sugar', 'restecg', 'max_hr', 'exang', 'oldpeak', 'slope', 11 | 'num_major_vessels', 'thal'] 12 | # Categorical features that needs to be one hot encoded 13 | FEATURES_TO_ENCODE = ['thal', 'slope', 'chest_pain_type', 'restecg'] 14 | # Feature names after one hot encoding 15 | ONE_HOT_ENCODED_FEATURES = ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 16 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 17 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 18 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 19 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'] 20 | -------------------------------------------------------------------------------- /exception handling and logging/constants.py: -------------------------------------------------------------------------------- 1 | ''' 2 | constants.py contains all variables 3 | where constant values are assigned 4 | ''' 5 | 6 | # Latest model to be used in the inference process 7 | MODEL_NAME = 'aditya_model1_adaboost.joblib' 8 | # Column names of the source tabular data 9 | ORIGINAL_FEATURES = ['age', 'sex', 'chest_pain_type', 'resting_bp', 'cholestoral', 10 | 'fasting_blood_sugar', 'restecg', 'max_hr', 'exang', 'oldpeak', 'slope', 11 | 'num_major_vessels', 'thal'] 12 | # Categorical features that needs to be one hot encoded 13 | FEATURES_TO_ENCODE = ['thal', 'slope', 'chest_pain_type', 'restecg'] 14 | # Feature names after one hot encoding 15 | ONE_HOT_ENCODED_FEATURES = ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 16 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 17 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 18 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 19 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'] 20 | -------------------------------------------------------------------------------- /docker_commands.txt: -------------------------------------------------------------------------------- 1 | # Build Image 2 | docker build -t fastapideploy . 3 | 4 | # Run Container 5 | docker run -d --name dockercontainer -p 80:8000 fastapideploy 6 | 7 | # PS 8 | docker ps --- Show running containers 9 | docker ps -a --- Show all containers 10 | 11 | # Show Images 12 | docker images 13 | 14 | # Remove 15 | docker rm dockercontainer -- remove container 16 | docker rmi fastapideploy -- remove image 17 | 18 | # Docker Hub 19 | -- Create Repository from Hub 20 | 21 | # Create Tag/Re-Tag Image 22 | docker tag fastapideploy adib0073/fastapi_ml_deploy:fastapideploy 23 | 24 | # Commit Container 25 | docker commit dockercontainer adib0073/fastapi_ml_deploy:fastapideploy 26 | 27 | # Push Container 28 | docker push adib0073/fastapi_ml_deploy:fastapideploy 29 | 30 | # Pull Docker Images 31 | docker pull adib0073/fastapi_ml_deploy:fastapideploy 32 | 33 | ============================================ 34 | # Build a Docker image 35 | $ docker build -t [image_name]:[tag] . 36 | 37 | # Run a Docker container specifying a name 38 | $ docker run --name [container_name] [image_name]:[tag] 39 | $ docker run -p [host:host] [image_name] 40 | 41 | # Fetch the logs of a container 42 | $ docker logs -f [container_id_or_name] 43 | 44 | # Run a command in a running container 45 | $ docker exec -it [container_id_or_name] bash 46 | 47 | # Show running containers 48 | $ docker ps 49 | 50 | # Show all containers 51 | $ docker ps -a 52 | 53 | # Show Docker images 54 | $ docker images 55 | 56 | # Stop a Docker container 57 | $ docker stop [container_id_or_name] 58 | 59 | # Remove a Docker container 60 | $ docker rm [container_id_or_name] 61 | 62 | # Remove a Docker image 63 | $ docker rmi [image_id_or_name] -------------------------------------------------------------------------------- /code documentation/utils.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | from sklearn import preprocessing 4 | from constants import * 5 | 6 | 7 | def get_inference_data(): 8 | data = pd.read_csv("Data/inference_heart_disease.csv") # Live connection to the database 9 | data.drop_duplicates(subset=None, inplace=True) 10 | data.duplicated().any() 11 | 12 | return data[data.columns.drop('target')], data['target'] 13 | 14 | 15 | def encode_features(df, features): 16 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) 17 | placeholder_df = pd.DataFrame() 18 | 19 | for f in features: 20 | if(f in df.columns): 21 | encoded = pd.get_dummies(df[f]) 22 | encoded = encoded.add_prefix(f + '_') 23 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 24 | else: 25 | print('Feature not found') 26 | return df 27 | 28 | for feature in encoded_df.columns: 29 | if feature in df.columns: 30 | encoded_df[feature] = df[feature] 31 | if feature in placeholder_df.columns: 32 | encoded_df[feature] = placeholder_df[feature] 33 | encoded_df.fillna(0, inplace=True) 34 | 35 | return encoded_df 36 | 37 | def normalize_data(df): 38 | val = df.values 39 | min_max_normalizer = preprocessing.MinMaxScaler() 40 | norm_val = min_max_normalizer.fit_transform(val) 41 | df2 = pd.DataFrame(norm_val) 42 | 43 | return df2 44 | 45 | def apply_pre_processing(data): 46 | features_to_encode = FEATURES_TO_ENCODE 47 | encoded = encode_features(data, features_to_encode) 48 | processed_data = normalize_data(encoded) 49 | 50 | return processed_data 51 | -------------------------------------------------------------------------------- /uci_heart_disease/utils.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | from sklearn import preprocessing 4 | from constants import * 5 | 6 | 7 | def get_inference_data(): 8 | data = pd.read_csv("Data/inference_heart_disease.csv") # Live connection to the database 9 | data.drop_duplicates(subset=None, inplace=True) 10 | data.duplicated().any() 11 | 12 | return data[data.columns.drop('target')], data['target'] 13 | 14 | 15 | def encode_features(df, features): 16 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) # from constants.py 17 | placeholder_df = pd.DataFrame() 18 | 19 | for f in features: 20 | if(f in df.columns): 21 | encoded = pd.get_dummies(df[f]) 22 | encoded = encoded.add_prefix(f + '_') 23 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 24 | else: 25 | print('Feature not found') 26 | return df 27 | 28 | for feature in encoded_df.columns: 29 | if feature in df.columns: 30 | encoded_df[feature] = df[feature] 31 | if feature in placeholder_df.columns: 32 | encoded_df[feature] = placeholder_df[feature] 33 | encoded_df.fillna(0, inplace=True) 34 | 35 | return encoded_df 36 | 37 | 38 | def normalize_data(df): 39 | val = df.values 40 | min_max_normalizer = preprocessing.MinMaxScaler() 41 | norm_val = min_max_normalizer.fit_transform(val) 42 | df2 = pd.DataFrame(norm_val) 43 | 44 | return df2 45 | 46 | 47 | def apply_pre_processing(data): 48 | features_to_encode = FEATURES_TO_ENCODE 49 | encoded = encode_features(data, features_to_encode) 50 | processed_data = normalize_data(encoded) 51 | 52 | return processed_data 53 | -------------------------------------------------------------------------------- /docker_deploy/app/utils.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | from sklearn import preprocessing 4 | from constants import * 5 | 6 | 7 | # apply same pre-processing and feature engineering techniques as applied during the training process 8 | def encode_features(df, features): 9 | ''' 10 | Method for one-hot encoding all selected categorical fields 11 | ''' 12 | # Implement these steps to prevent dimension mismatch during inference 13 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) # from constants.py 14 | placeholder_df = pd.DataFrame() 15 | 16 | # One-Hot Encoding using get_dummies for the specified categorical features 17 | for f in features: 18 | if(f in df.columns): 19 | encoded = pd.get_dummies(df[f]) 20 | encoded = encoded.add_prefix(f + '_') 21 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 22 | else: 23 | print('Feature not found') 24 | return df 25 | 26 | # Implement these steps to prevent dimension mismatch during inference 27 | for feature in encoded_df.columns: 28 | if feature in df.columns: 29 | encoded_df[feature] = df[feature] 30 | if feature in placeholder_df.columns: 31 | encoded_df[feature] = placeholder_df[feature] 32 | # fill all null values 33 | encoded_df.fillna(0, inplace=True) 34 | 35 | return encoded_df 36 | 37 | def normalize_data(df): 38 | val = df.values 39 | min_max_normalizer = preprocessing.MinMaxScaler() 40 | norm_val = min_max_normalizer.fit_transform(val) 41 | df2 = pd.DataFrame(norm_val) 42 | 43 | return df2 44 | 45 | def apply_pre_processing(data): 46 | features_to_encode = FEATURES_TO_ENCODE # from constants.py 47 | encoded = encode_features(data, features_to_encode) 48 | processed_data = normalize_data(encoded) 49 | return processed_data -------------------------------------------------------------------------------- /exception handling and logging/inference_pipe_exec.log: -------------------------------------------------------------------------------- 1 | 2022-06-21 15:00:28,277 Started execution. Fetching data now ... 2 | 2022-06-21 15:00:28,281 Encountered error. Please check. 3 | 2022-06-21 15:00:28,281 [Errno 2] No such file or directory: 'Data/heart.csv' 4 | 2022-06-21 15:01:00,426 Started execution. Fetching data now ... 5 | 2022-06-21 15:01:00,450 Data fetched. Applying pre-processing now ... 6 | 2022-06-21 15:01:00,466 Pre-processing is completed. Loading trained model now ... 7 | 2022-06-21 15:01:00,634 Trained model is loaded. Executing trained model on inference data ... 8 | 2022-06-21 15:01:00,650 Execution is complete. 9 | 2022-07-03 14:04:07,785 Started execution. Fetching data now ... 10 | 2022-07-03 14:04:07,801 Data fetched. Applying pre-processing now ... 11 | 2022-07-03 14:04:07,850 Pre-processing is completed. Loading trained model now ... 12 | 2022-07-03 14:04:08,061 Trained model is loaded. Executing trained model on inference data ... 13 | 2022-07-03 14:04:08,077 Execution is complete. 14 | 2022-07-04 19:36:21,404 Started execution. Fetching data now ... 15 | 2022-07-04 19:36:21,413 Data fetched. Applying pre-processing now ... 16 | 2022-07-04 19:36:21,424 Pre-processing is completed. Loading trained model now ... 17 | 2022-07-04 19:36:21,634 Trained model is loaded. Executing trained model on inference data ... 18 | 2022-07-04 19:36:21,648 Execution is complete. 19 | 2022-07-04 19:39:06,750 Started execution. Fetching data now ... 20 | 2022-07-04 19:39:06,760 Data fetched. Applying pre-processing now ... 21 | 2022-07-04 19:39:06,773 Pre-processing is completed. Loading trained model now ... 22 | 2022-07-04 19:39:06,988 Trained model is loaded. Executing trained model on inference data ... 23 | 2022-07-04 19:39:07,004 Execution is complete. 24 | 2022-07-04 19:41:07,090 Started execution. Fetching data now ... 25 | 2022-07-04 19:41:07,091 Encountered error. Please check. 26 | 2022-07-04 19:41:07,091 [Errno 2] No such file or directory: 'Data/inference_heart_disease.csv' 27 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | anyio==3.3.4 2 | argcomplete==1.12.3 3 | argon2-cffi==21.1.0 4 | asgiref==3.4.1 5 | atomicwrites==1.4.0 6 | attrs==21.2.0 7 | backcall==0.2.0 8 | bleach==4.1.0 9 | cffi==1.15.0 10 | click==8.0.3 11 | colorama==0.4.4 12 | cvxopt==1.2.7 13 | cvxpy==1.1.15 14 | cycler==0.10.0 15 | debugpy==1.5.1 16 | decorator==5.1.0 17 | defusedxml==0.7.1 18 | ecos==2.0.7.post1 19 | entrypoints==0.3 20 | fancyimpute==0.7.0 21 | fastapi==0.70.0 22 | h11==0.12.0 23 | httptools==0.2.0 24 | idna==3.3 25 | importlib-metadata==4.8.1 26 | iniconfig==1.1.1 27 | ipykernel==6.4.2 28 | ipython==7.28.0 29 | ipython-genutils==0.2.0 30 | jedi==0.18.0 31 | Jinja2==3.0.2 32 | joblib==1.1.0 33 | jsonschema==4.1.2 34 | jupyter-client==7.0.6 35 | jupyter-core==4.8.1 36 | jupyterlab-pygments==0.1.2 37 | kiwisolver==1.3.2 38 | knnimpute==0.1.0 39 | MarkupSafe==2.0.1 40 | matplotlib==3.4.3 41 | matplotlib-inline==0.1.3 42 | mistune==0.8.4 43 | nbclient==0.5.4 44 | nbconvert==6.2.0 45 | nbformat==5.1.3 46 | nest-asyncio==1.5.1 47 | nose==1.3.7 48 | notebook==6.4.5 49 | numpy==1.21.3 50 | osqp==0.6.2.post0 51 | packaging==21.0 52 | pandas==1.3.4 53 | pandocfilters==1.5.0 54 | parso==0.8.2 55 | pickleshare==0.7.5 56 | Pillow==8.4.0 57 | pluggy==1.0.0 58 | prometheus-client==0.11.0 59 | prompt-toolkit==3.0.21 60 | py==1.10.0 61 | pycparser==2.20 62 | pydantic==1.8.2 63 | Pygments==2.10.0 64 | pyparsing==2.4.7 65 | pyrsistent==0.18.0 66 | pytest==6.2.5 67 | python-dateutil==2.8.2 68 | python-dotenv==0.19.1 69 | pytz==2021.3 70 | pywin32==302 71 | pywinpty==1.1.4 72 | PyYAML==6.0 73 | pyzmq==22.3.0 74 | qdldl==0.1.5.post0 75 | scikit-learn==1.0 76 | scipy==1.7.1 77 | scs==2.1.4 78 | seaborn==0.11.2 79 | Send2Trash==1.8.0 80 | six==1.16.0 81 | sniffio==1.2.0 82 | starlette==0.16.0 83 | terminado==0.12.1 84 | testpath==0.5.0 85 | threadpoolctl==3.0.0 86 | toml==0.10.2 87 | tornado==6.1 88 | traitlets==5.1.0 89 | typing-extensions==3.10.0.2 90 | uvicorn==0.15.0 91 | watchgod==0.7 92 | wcwidth==0.2.5 93 | webencodings==0.5.1 94 | websockets==10.0 95 | zipp==3.6.0 96 | -------------------------------------------------------------------------------- /python scripting/main.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Inference 5 | # In this script, we will try to look at 6 | # the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | import warnings 10 | warnings.filterwarnings("ignore") 11 | import pandas as pd 12 | import numpy as np 13 | import joblib 14 | from sklearn.metrics import accuracy_score 15 | from utils import * 16 | from constants import * 17 | import argparse 18 | 19 | 20 | # main function - starting point of the code 21 | def main(model_name): 22 | ''' 23 | main function - starting point of the code 24 | input: model name taken as input 25 | (default: adaboost model) 26 | output: no return value, only prints outcome 27 | ''' 28 | print("Starting execution of the inference code...") 29 | # in real-time use cases, this code should be replaced with live flowing data 30 | # use get_inference_data() from utils.py to fetch inference data 31 | inference_data, labels = get_inference_data() 32 | # use apply_pre_processing() from utils.py 33 | # to apply necessary preprocessing as applied for training data 34 | processed_inference_data = apply_pre_processing(inference_data) 35 | # ### Load Saved Model 36 | model = joblib.load(model_name) 37 | # ### Prediction on inference data 38 | model.predict(processed_inference_data) 39 | # ### Scoring check on prediction 40 | print("Checking inference accuracy:") 41 | print(accuracy_score(labels, model.predict(processed_inference_data))) 42 | 43 | 44 | if __name__ == "__main__": 45 | parser = argparse.ArgumentParser(description='Running inference pipeline') 46 | parser.add_argument('--model', 47 | default='adaboost', 48 | help='select algorithm: svm or adaboost') 49 | args = parser.parse_args() 50 | print(f"Selected algorithm: {args.model}") 51 | if(args.model == 'svm'): 52 | model_name = 'aditya_model2_svm.joblib' 53 | else: 54 | model_name = 'aditya_model1_adaboost.joblib' 55 | main(model_name) 56 | -------------------------------------------------------------------------------- /docker_deploy/app/main.py: -------------------------------------------------------------------------------- 1 | import joblib 2 | from fastapi import FastAPI 3 | from constants import * 4 | from utils import * 5 | from data_model import * 6 | 7 | 8 | app = FastAPI() 9 | model = joblib.load(MODEL_NAME) # Load from constants 10 | 11 | def apply_model(model, inference_data): 12 | # Prepare prediction dataframe 13 | inf_df = pd.DataFrame([[inference_data.age, 14 | inference_data.sex, 15 | inference_data.chest_pain_type, 16 | inference_data.resting_bp, 17 | inference_data.cholestoral, 18 | inference_data.fasting_blood_sugar, 19 | inference_data.restecg, 20 | inference_data.max_hr, 21 | inference_data.exang, 22 | inference_data.oldpeak, 23 | inference_data.slope, 24 | inference_data.num_major_vessels, 25 | inference_data.thal]], columns = ORIGINAL_FEATURES) 26 | inf_df[ORIGINAL_FEATURES[0]] = inference_data.age 27 | inf_df[ORIGINAL_FEATURES[1]] = inference_data.sex 28 | inf_df[ORIGINAL_FEATURES[2]] = inference_data.chest_pain_type 29 | inf_df[ORIGINAL_FEATURES[3]] = inference_data.resting_bp 30 | inf_df[ORIGINAL_FEATURES[4]] = inference_data.cholestoral 31 | inf_df[ORIGINAL_FEATURES[5]] = inference_data.fasting_blood_sugar 32 | inf_df[ORIGINAL_FEATURES[6]] = inference_data.restecg 33 | inf_df[ORIGINAL_FEATURES[7]] = inference_data.max_hr 34 | inf_df[ORIGINAL_FEATURES[8]] = inference_data.exang 35 | inf_df[ORIGINAL_FEATURES[9]] = inference_data.oldpeak 36 | inf_df[ORIGINAL_FEATURES[10]] = inference_data.slope 37 | inf_df[ORIGINAL_FEATURES[11]] = inference_data.num_major_vessels 38 | inf_df[ORIGINAL_FEATURES[12]] = inference_data.thal 39 | 40 | processed_inference_data = apply_pre_processing(inf_df) 41 | pred = model.predict(processed_inference_data)[0] 42 | 43 | if pred == 1: 44 | pred_value = True 45 | pred_class = "heart disease" 46 | else: 47 | pred_value = False 48 | pred_class = "No heart disease" 49 | 50 | return pred_value, pred_class 51 | 52 | @app.get('/') 53 | def get_root(): 54 | 55 | return {'message': 'Welcome to the Heart Disease Detection API'} 56 | 57 | @app.post("/predict", response_model=OutputDataModel) 58 | async def post_predictions(inference_data: InputDataModel): 59 | 60 | pred_value, pred_class = apply_model(model, inference_data) 61 | 62 | response = { 63 | "predicted_value": pred_value, 64 | "predicted_class": pred_class 65 | } 66 | return response -------------------------------------------------------------------------------- /uci_heart_disease/main.py: -------------------------------------------------------------------------------- 1 | import joblib 2 | from fastapi import FastAPI 3 | from constants import * 4 | from utils import * 5 | from data_model import * 6 | 7 | 8 | app = FastAPI() 9 | model = joblib.load(MODEL_NAME) # Load from constants 10 | 11 | def apply_model(model, inference_data): 12 | # Prepare prediction dataframe 13 | inf_df = pd.DataFrame([[inference_data.age, 14 | inference_data.sex, 15 | inference_data.chest_pain_type, 16 | inference_data.resting_bp, 17 | inference_data.cholestoral, 18 | inference_data.fasting_blood_sugar, 19 | inference_data.restecg, 20 | inference_data.max_hr, 21 | inference_data.exang, 22 | inference_data.oldpeak, 23 | inference_data.slope, 24 | inference_data.num_major_vessels, 25 | inference_data.thal]], columns = ORIGINAL_FEATURES) 26 | inf_df[ORIGINAL_FEATURES[0]] = inference_data.age 27 | inf_df[ORIGINAL_FEATURES[1]] = inference_data.sex 28 | inf_df[ORIGINAL_FEATURES[2]] = inference_data.chest_pain_type 29 | inf_df[ORIGINAL_FEATURES[3]] = inference_data.resting_bp 30 | inf_df[ORIGINAL_FEATURES[4]] = inference_data.cholestoral 31 | inf_df[ORIGINAL_FEATURES[5]] = inference_data.fasting_blood_sugar 32 | inf_df[ORIGINAL_FEATURES[6]] = inference_data.restecg 33 | inf_df[ORIGINAL_FEATURES[7]] = inference_data.max_hr 34 | inf_df[ORIGINAL_FEATURES[8]] = inference_data.exang 35 | inf_df[ORIGINAL_FEATURES[9]] = inference_data.oldpeak 36 | inf_df[ORIGINAL_FEATURES[10]] = inference_data.slope 37 | inf_df[ORIGINAL_FEATURES[11]] = inference_data.num_major_vessels 38 | inf_df[ORIGINAL_FEATURES[12]] = inference_data.thal 39 | 40 | processed_inference_data = apply_pre_processing(inf_df) 41 | pred = model.predict(processed_inference_data)[0] 42 | 43 | if pred == 1: 44 | pred_value = True 45 | pred_class = "heart disease" 46 | else: 47 | pred_value = False 48 | pred_class = "No heart disease" 49 | 50 | return pred_value, pred_class 51 | 52 | @app.get('/') 53 | def get_root(): 54 | 55 | return {'message': 'Welcome to the Heart Disease Detection API'} 56 | 57 | @app.post("/predict", response_model=OutputDataModel) 58 | async def post_predictions(inference_data: InputDataModel): 59 | 60 | pred_value, pred_class = apply_model(model, inference_data) 61 | 62 | response = { 63 | "predicted_value": pred_value, 64 | "predicted_class": pred_class 65 | } 66 | return response 67 | -------------------------------------------------------------------------------- /exception handling and logging/main.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Inference 5 | # In this script, we will try to look at 6 | # the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | import warnings 10 | warnings.filterwarnings("ignore") 11 | import pandas as pd 12 | import numpy as np 13 | import joblib 14 | from sklearn.metrics import accuracy_score 15 | from utils import * 16 | from constants import * 17 | import argparse 18 | import logging 19 | 20 | 21 | # main function - starting point of the code 22 | def main(model_name, logger): 23 | ''' 24 | main function - starting point of the code 25 | input: model name taken as input 26 | (default: adaboost model) 27 | output: no return value, only prints outcome 28 | ''' 29 | try: 30 | print("Starting execution of the inference code...") 31 | logger.info("Started execution. Fetching data now ...") 32 | # in real-time use cases, this code should be replaced with live flowing data 33 | # use get_inference_data() from utils.py to fetch inference data 34 | inference_data, labels = get_inference_data() 35 | logger.info("Data fetched. Applying pre-processing now ...") 36 | # use apply_pre_processing() from utils.py 37 | # to apply necessary preprocessing as applied for training data 38 | processed_inference_data = apply_pre_processing(inference_data) 39 | logger.info("Pre-processing is completed. Loading trained model now ...") 40 | # ### Load Saved Model 41 | model = joblib.load(model_name) 42 | logger.info("Trained model is loaded. Executing trained model on inference data ...") 43 | # ### Prediction on inference data 44 | model.predict(processed_inference_data) 45 | # ### Scoring check on prediction 46 | print("Checking inference accuracy:") 47 | print(accuracy_score(labels, model.predict(processed_inference_data))) 48 | logger.info("Execution is complete.") 49 | except Exception as e: 50 | print("--------Error!!!--------") 51 | logger.error("Encountered error. Please check.") 52 | logger.error(e) 53 | print(e) 54 | 55 | 56 | if __name__ == "__main__": 57 | # Create and configure logger 58 | logging.basicConfig(filename="inference_pipe_exec.log", 59 | format='%(asctime)s %(message)s', 60 | filemode='a') 61 | 62 | # Creating an object 63 | logger = logging.getLogger() 64 | 65 | # Setting the threshold of logger to DEBUG 66 | logger.setLevel(logging.DEBUG) 67 | 68 | parser = argparse.ArgumentParser(description='Running inference pipeline') 69 | parser.add_argument('--model', 70 | default='adaboost', 71 | help='select algorithm: svm or adaboost') 72 | args = parser.parse_args() 73 | print(f"Selected algorithm: {args.model}") 74 | if(args.model == 'svm'): 75 | model_name = 'aditya_model2_svm.joblib' 76 | else: 77 | model_name = 'aditya_model1_adaboost.joblib' 78 | main(model_name, logger) 79 | -------------------------------------------------------------------------------- /code linting/Corrected/utils.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Utils.py contains all utility functions 3 | used during the inference process 4 | ''' 5 | 6 | import pandas as pd 7 | import numpy as np 8 | from sklearn import preprocessing 9 | from constants import * 10 | 11 | 12 | def get_inference_data(): 13 | ''' 14 | Method for loading inference data 15 | Input: No input 16 | Output: Returns inference data features and labels 17 | Example usage: inference_data, labels = get_inference_data() 18 | ''' 19 | # Live connection to the database 20 | data = pd.read_csv("Data/inference_heart_disease.csv") 21 | data.drop_duplicates(subset=None, inplace=True) 22 | data.duplicated().any() 23 | return data[data.columns.drop('target')], data['target'] 24 | 25 | 26 | # apply same pre-processing and feature engineering techniques 27 | # as applied during the training process 28 | def encode_features(df, features): 29 | ''' 30 | Method for one-hot encoding all selected categorical fields 31 | Input: The method takes pandas dataframe and 32 | list of the feature names as input 33 | Output: Returns a dataframe with one-hot encoded features 34 | Example usage: 35 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 36 | ''' 37 | # Implement these steps to prevent dimension mismatch during inference 38 | # from constants.py 39 | encoded_df = pd.DataFrame(columns=ONE_HOT_ENCODED_FEATURES) 40 | placeholder_df = pd.DataFrame() 41 | # One-Hot Encoding using get_dummies for the specified categorical features 42 | for f in features: 43 | if(f in df.columns): 44 | encoded = pd.get_dummies(df[f]) 45 | encoded = encoded.add_prefix(f + '_') 46 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 47 | else: 48 | print('Feature not found') 49 | return df 50 | # Implement these steps to prevent dimension mismatch during inference 51 | for feature in encoded_df.columns: 52 | if feature in df.columns: 53 | encoded_df[feature] = df[feature] 54 | if feature in placeholder_df.columns: 55 | encoded_df[feature] = placeholder_df[feature] 56 | # fill all null values 57 | encoded_df.fillna(0, inplace=True) 58 | return encoded_df 59 | 60 | 61 | def normalize_data(df): 62 | ''' 63 | Normalize data using Min-Max Scaler 64 | Input: The method takes pandas dataframe as input 65 | Output: Returns a dataframe with normalized features 66 | Example usage: 67 | normalized_df = normalize_data(df) 68 | ''' 69 | values = df.values 70 | min_max_normalizer = preprocessing.MinMaxScaler() 71 | norm_val = min_max_normalizer.fit_transform(values) 72 | norm_df = pd.DataFrame(norm_val) 73 | return norm_df 74 | 75 | 76 | def apply_pre_processing(data): 77 | ''' 78 | Apply all pre-processing methods together 79 | Input: The method takes the inference data as pandas dataframe as input 80 | Output: Returns a dataframe after applying all preprocessing steps 81 | Example usage: 82 | processed_data = apply_pre_processing(df) 83 | ''' 84 | features_to_encode = FEATURES_TO_ENCODE # from constants.py 85 | # applying encoded features function 86 | encoded = encode_features(data, features_to_encode) 87 | processed_data = normalize_data(encoded) # applying normalization function 88 | return processed_data 89 | -------------------------------------------------------------------------------- /code linting/utils.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Utils.py contains all utility functions 3 | used during the inference process 4 | ''' 5 | 6 | import pandas as pd 7 | import numpy as np 8 | from sklearn import preprocessing 9 | from constants import * 10 | 11 | 12 | def get_inference_data(): 13 | ''' 14 | Method for loading inference data 15 | Input: No input 16 | Output: Returns inference data features and labels 17 | Example usage: inference_data, labels = get_inference_data() 18 | ''' 19 | # Live connection to the database 20 | data = pd.read_csv("Data/inference_heart_disease.csv") 21 | data.drop_duplicates(subset=None, inplace=True) 22 | data.duplicated().any() 23 | return data[data.columns.drop('target')], data['target'] 24 | 25 | 26 | # apply same pre-processing and feature engineering techniques as applied during the training process 27 | def encode_features(df, features): 28 | ''' 29 | Method for one-hot encoding all selected categorical fields 30 | Input: The method takes pandas dataframe and 31 | list of the feature names as input 32 | Output: Returns a dataframe with one-hot encoded features 33 | Example usage: 34 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 35 | ''' 36 | # Implement these steps to prevent dimension mismatch during inference 37 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) # from constants.py 38 | placeholder_df = pd.DataFrame() 39 | 40 | # One-Hot Encoding using get_dummies for the specified categorical features 41 | for f in features: 42 | if(f in df.columns): 43 | encoded = pd.get_dummies(df[f]) 44 | encoded = encoded.add_prefix(f + '_') 45 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 46 | else: 47 | print('Feature not found') 48 | return df 49 | 50 | # Implement these steps to prevent dimension mismatch during inference 51 | for feature in encoded_df.columns: 52 | if feature in df.columns: 53 | encoded_df[feature] = df[feature] 54 | if feature in placeholder_df.columns: 55 | encoded_df[feature] = placeholder_df[feature] 56 | # fill all null values 57 | encoded_df.fillna(0, inplace=True) 58 | 59 | return encoded_df 60 | 61 | def normalize_data(df): 62 | ''' 63 | Normalize data using Min-Max Scaler 64 | Input: The method takes pandas dataframe as input 65 | Output: Returns a dataframe with normalized features 66 | Example usage: 67 | normalized_df = normalize_data(df) 68 | ''' 69 | values = df.values 70 | min_max_normalizer = preprocessing.MinMaxScaler() 71 | norm_val = min_max_normalizer.fit_transform(values) 72 | norm_df = pd.DataFrame(norm_val) 73 | 74 | return norm_df 75 | 76 | def apply_pre_processing(data): 77 | ''' 78 | Apply all pre-processing methods together 79 | Input: The method takes the inference data as pandas dataframe as input 80 | Output: Returns a dataframe after applying all preprocessing steps 81 | Example usage: 82 | processed_data = apply_pre_processing(df) 83 | ''' 84 | features_to_encode = FEATURES_TO_ENCODE # from constants.py 85 | encoded = encode_features(data, features_to_encode) # applying encoded features function 86 | processed_data = normalize_data(encoded) # applying normalization function 87 | 88 | return processed_data 89 | -------------------------------------------------------------------------------- /python scripting/utils.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Utils.py contains all utility functions 3 | used during the inference process 4 | ''' 5 | 6 | import pandas as pd 7 | import numpy as np 8 | from sklearn import preprocessing 9 | from constants import * 10 | 11 | 12 | def get_inference_data(): 13 | ''' 14 | Method for loading inference data 15 | Input: No input 16 | Output: Returns inference data features and labels 17 | Example usage: inference_data, labels = get_inference_data() 18 | ''' 19 | data = pd.read_csv("Data/inference_heart_disease.csv") # Live connection to the database 20 | data.drop_duplicates(subset=None, inplace=True) 21 | data.duplicated().any() 22 | 23 | return data[data.columns.drop('target')], data['target'] 24 | 25 | 26 | # apply same pre-processing and feature engineering techniques as applied during the training process 27 | def encode_features(df, features): 28 | ''' 29 | Method for one-hot encoding all selected categorical fields 30 | Input: The method takes pandas dataframe and 31 | list of the feature names as input 32 | Output: Returns a dataframe with one-hot encoded features 33 | Example usage: 34 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 35 | ''' 36 | # Implement these steps to prevent dimension mismatch during inference 37 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) # from constants.py 38 | placeholder_df = pd.DataFrame() 39 | 40 | # One-Hot Encoding using get_dummies for the specified categorical features 41 | for f in features: 42 | if(f in df.columns): 43 | encoded = pd.get_dummies(df[f]) 44 | encoded = encoded.add_prefix(f + '_') 45 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 46 | else: 47 | print('Feature not found') 48 | return df 49 | 50 | # Implement these steps to prevent dimension mismatch during inference 51 | for feature in encoded_df.columns: 52 | if feature in df.columns: 53 | encoded_df[feature] = df[feature] 54 | if feature in placeholder_df.columns: 55 | encoded_df[feature] = placeholder_df[feature] 56 | # fill all null values 57 | encoded_df.fillna(0, inplace=True) 58 | 59 | return encoded_df 60 | 61 | def normalize_data(df): 62 | ''' 63 | Normalize data using Min-Max Scaler 64 | Input: The method takes pandas dataframe as input 65 | Output: Returns a dataframe with normalized features 66 | Example usage: 67 | normalized_df = normalize_data(df) 68 | ''' 69 | values = df.values 70 | min_max_normalizer = preprocessing.MinMaxScaler() 71 | norm_val = min_max_normalizer.fit_transform(values) 72 | norm_df = pd.DataFrame(norm_val) 73 | 74 | return norm_df 75 | 76 | def apply_pre_processing(data): 77 | ''' 78 | Apply all pre-processing methods together 79 | Input: The method takes the inference data as pandas dataframe as input 80 | Output: Returns a dataframe after applying all preprocessing steps 81 | Example usage: 82 | processed_data = apply_pre_processing(df) 83 | ''' 84 | features_to_encode = FEATURES_TO_ENCODE # from constants.py 85 | encoded = encode_features(data, features_to_encode) # applying encoded features function 86 | processed_data = normalize_data(encoded) # applying normalization function 87 | 88 | return processed_data 89 | -------------------------------------------------------------------------------- /unit testing/utils.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Utils.py contains all utility functions 3 | used during the inference process 4 | ''' 5 | 6 | import pandas as pd 7 | import numpy as np 8 | from sklearn import preprocessing 9 | from constants import * 10 | 11 | 12 | def get_inference_data(): 13 | ''' 14 | Method for loading inference data 15 | Input: No input 16 | Output: Returns inference data features and labels 17 | Example usage: inference_data, labels = get_inference_data() 18 | ''' 19 | data = pd.read_csv("Data/inference_heart_disease.csv") # Live connection to the database 20 | data.drop_duplicates(subset=None, inplace=True) 21 | data.duplicated().any() 22 | 23 | return data[data.columns.drop('target')], data['target'] 24 | 25 | 26 | # apply same pre-processing and feature engineering techniques as applied during the training process 27 | def encode_features(df, features): 28 | ''' 29 | Method for one-hot encoding all selected categorical fields 30 | Input: The method takes pandas dataframe and 31 | list of the feature names as input 32 | Output: Returns a dataframe with one-hot encoded features 33 | Example usage: 34 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 35 | ''' 36 | # Implement these steps to prevent dimension mismatch during inference 37 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) # from constants.py 38 | placeholder_df = pd.DataFrame() 39 | 40 | # One-Hot Encoding using get_dummies for the specified categorical features 41 | for f in features: 42 | if(f in df.columns): 43 | encoded = pd.get_dummies(df[f]) 44 | encoded = encoded.add_prefix(f + '_') 45 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 46 | else: 47 | print('Feature not found') 48 | return df 49 | 50 | # Implement these steps to prevent dimension mismatch during inference 51 | for feature in encoded_df.columns: 52 | if feature in df.columns: 53 | encoded_df[feature] = df[feature] 54 | if feature in placeholder_df.columns: 55 | encoded_df[feature] = placeholder_df[feature] 56 | # fill all null values 57 | encoded_df.fillna(0, inplace=True) 58 | 59 | return encoded_df 60 | 61 | def normalize_data(df): 62 | ''' 63 | Normalize data using Min-Max Scaler 64 | Input: The method takes pandas dataframe as input 65 | Output: Returns a dataframe with normalized features 66 | Example usage: 67 | normalized_df = normalize_data(df) 68 | ''' 69 | values = df.values 70 | min_max_normalizer = preprocessing.MinMaxScaler() 71 | norm_val = min_max_normalizer.fit_transform(values) 72 | norm_df = pd.DataFrame(norm_val) 73 | 74 | return norm_df 75 | 76 | def apply_pre_processing(data): 77 | ''' 78 | Apply all pre-processing methods together 79 | Input: The method takes the inference data as pandas dataframe as input 80 | Output: Returns a dataframe after applying all preprocessing steps 81 | Example usage: 82 | processed_data = apply_pre_processing(df) 83 | ''' 84 | features_to_encode = FEATURES_TO_ENCODE # from constants.py 85 | encoded = encode_features(data, features_to_encode) # applying encoded features function 86 | processed_data = normalize_data(encoded) # applying normalization function 87 | 88 | return processed_data 89 | -------------------------------------------------------------------------------- /code documentation/Corrected/utils.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Utils.py contains all utility functions 3 | used during the inference process 4 | ''' 5 | 6 | import pandas as pd 7 | import numpy as np 8 | from sklearn import preprocessing 9 | from constants import * 10 | 11 | 12 | def get_inference_data(): 13 | ''' 14 | Method for loading inference data 15 | Input: No input 16 | Output: Returns inference data features and labels 17 | Example usage: inference_data, labels = get_inference_data() 18 | ''' 19 | data = pd.read_csv("Data/inference_heart_disease.csv") # Live connection to the database 20 | data.drop_duplicates(subset=None, inplace=True) 21 | data.duplicated().any() 22 | 23 | return data[data.columns.drop('target')], data['target'] 24 | 25 | 26 | # apply same pre-processing and feature engineering techniques as applied during the training process 27 | def encode_features(df, features): 28 | ''' 29 | Method for one-hot encoding all selected categorical fields 30 | Input: The method takes pandas dataframe and 31 | list of the feature names as input 32 | Output: Returns a dataframe with one-hot encoded features 33 | Example usage: 34 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 35 | ''' 36 | # Implement these steps to prevent dimension mismatch during inference 37 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) # from constants.py 38 | placeholder_df = pd.DataFrame() 39 | 40 | # One-Hot Encoding using get_dummies for the specified categorical features 41 | for f in features: 42 | if(f in df.columns): 43 | encoded = pd.get_dummies(df[f]) 44 | encoded = encoded.add_prefix(f + '_') 45 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 46 | else: 47 | print('Feature not found') 48 | return df 49 | 50 | # Implement these steps to prevent dimension mismatch during inference 51 | for feature in encoded_df.columns: 52 | if feature in df.columns: 53 | encoded_df[feature] = df[feature] 54 | if feature in placeholder_df.columns: 55 | encoded_df[feature] = placeholder_df[feature] 56 | # fill all null values 57 | encoded_df.fillna(0, inplace=True) 58 | 59 | return encoded_df 60 | 61 | def normalize_data(df): 62 | ''' 63 | Normalize data using Min-Max Scaler 64 | Input: The method takes pandas dataframe as input 65 | Output: Returns a dataframe with normalized features 66 | Example usage: 67 | normalized_df = normalize_data(df) 68 | ''' 69 | values = df.values 70 | min_max_normalizer = preprocessing.MinMaxScaler() 71 | norm_val = min_max_normalizer.fit_transform(values) 72 | norm_df = pd.DataFrame(norm_val) 73 | 74 | return norm_df 75 | 76 | def apply_pre_processing(data): 77 | ''' 78 | Apply all pre-processing methods together 79 | Input: The method takes the inference data as pandas dataframe as input 80 | Output: Returns a dataframe after applying all preprocessing steps 81 | Example usage: 82 | processed_data = apply_pre_processing(df) 83 | ''' 84 | features_to_encode = FEATURES_TO_ENCODE # from constants.py 85 | encoded = encode_features(data, features_to_encode) # applying encoded features function 86 | processed_data = normalize_data(encoded) # applying normalization function 87 | 88 | return processed_data 89 | -------------------------------------------------------------------------------- /exception handling and logging/utils.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Utils.py contains all utility functions 3 | used during the inference process 4 | ''' 5 | 6 | import pandas as pd 7 | import numpy as np 8 | from sklearn import preprocessing 9 | from constants import * 10 | 11 | 12 | def get_inference_data(): 13 | ''' 14 | Method for loading inference data 15 | Input: No input 16 | Output: Returns inference data features and labels 17 | Example usage: inference_data, labels = get_inference_data() 18 | ''' 19 | data = pd.read_csv("Data/inference_heart_disease.csv") # Live connection to the database 20 | data.drop_duplicates(subset=None, inplace=True) 21 | data.duplicated().any() 22 | 23 | return data[data.columns.drop('target')], data['target'] 24 | 25 | 26 | # apply same pre-processing and feature engineering techniques as applied during the training process 27 | def encode_features(df, features): 28 | ''' 29 | Method for one-hot encoding all selected categorical fields 30 | Input: The method takes pandas dataframe and 31 | list of the feature names as input 32 | Output: Returns a dataframe with one-hot encoded features 33 | Example usage: 34 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 35 | ''' 36 | # Implement these steps to prevent dimension mismatch during inference 37 | encoded_df = pd.DataFrame(columns= ONE_HOT_ENCODED_FEATURES) # from constants.py 38 | placeholder_df = pd.DataFrame() 39 | 40 | # One-Hot Encoding using get_dummies for the specified categorical features 41 | for f in features: 42 | if(f in df.columns): 43 | encoded = pd.get_dummies(df[f]) 44 | encoded = encoded.add_prefix(f + '_') 45 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 46 | else: 47 | print('Feature not found') 48 | return df 49 | 50 | # Implement these steps to prevent dimension mismatch during inference 51 | for feature in encoded_df.columns: 52 | if feature in df.columns: 53 | encoded_df[feature] = df[feature] 54 | if feature in placeholder_df.columns: 55 | encoded_df[feature] = placeholder_df[feature] 56 | # fill all null values 57 | encoded_df.fillna(0, inplace=True) 58 | 59 | return encoded_df 60 | 61 | def normalize_data(df): 62 | ''' 63 | Normalize data using Min-Max Scaler 64 | Input: The method takes pandas dataframe as input 65 | Output: Returns a dataframe with normalized features 66 | Example usage: 67 | normalized_df = normalize_data(df) 68 | ''' 69 | values = df.values 70 | min_max_normalizer = preprocessing.MinMaxScaler() 71 | norm_val = min_max_normalizer.fit_transform(values) 72 | norm_df = pd.DataFrame(norm_val) 73 | 74 | return norm_df 75 | 76 | def apply_pre_processing(data): 77 | ''' 78 | Apply all pre-processing methods together 79 | Input: The method takes the inference data as pandas dataframe as input 80 | Output: Returns a dataframe after applying all preprocessing steps 81 | Example usage: 82 | processed_data = apply_pre_processing(df) 83 | ''' 84 | features_to_encode = FEATURES_TO_ENCODE # from constants.py 85 | encoded = encode_features(data, features_to_encode) # applying encoded features function 86 | processed_data = normalize_data(encoded) # applying normalization function 87 | 88 | return processed_data 89 | -------------------------------------------------------------------------------- /uci_heart_disease/Heart Disease Inference.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | # %% 4 | 5 | # ## Heart Disease Classification 6 | # 7 | # In this notebook, we will try to look at just the inference part of the heart disease classification solution 8 | 9 | # ### Import Modules 10 | 11 | # %% 12 | 13 | 14 | import pandas as pd 15 | import numpy as np 16 | from sklearn import preprocessing 17 | import joblib 18 | 19 | 20 | # ### Get Inference Data 21 | 22 | # %% 23 | 24 | 25 | # in real-time use cases, this method should be replaced with live flowing data 26 | def get_inference_data(): 27 | data = pd.read_csv("Data/heart.csv") 28 | data.drop_duplicates(subset=None, inplace=True) 29 | data.duplicated().any() 30 | inference_df = data.sample(frac=1, random_state = 2) 31 | inference_df = inference_df.tail(20) 32 | return inference_df[inference_df.columns.drop('target')], inference_df['target'] 33 | 34 | inference_data, labels = get_inference_data() 35 | 36 | 37 | # %% 38 | 39 | 40 | inference_data.columns 41 | 42 | 43 | # %% 44 | 45 | 46 | inference_data.head() 47 | 48 | 49 | # ### Apply Same Pre-processing 50 | 51 | # %% 52 | 53 | 54 | # apply same pre-processing and feature engineering techniques as applied during the training process 55 | def encode_features(df, features): 56 | ''' 57 | Method for one-hot encoding all selected categorical fields 58 | ''' 59 | # Implement these steps to prevent dimension mismatch during inference 60 | encoded_df = pd.DataFrame(columns= ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 61 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 62 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 63 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 64 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2']) 65 | placeholder_df = pd.DataFrame() 66 | 67 | # One-Hot Encoding using get_dummies for the specified categorical features 68 | for f in features: 69 | if(f in df.columns): 70 | encoded = pd.get_dummies(df[f]) 71 | encoded = encoded.add_prefix(f + '_') 72 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 73 | else: 74 | print('Feature not found') 75 | return df 76 | 77 | # Implement these steps to prevent dimension mismatch during inference 78 | for feature in encoded_df.columns: 79 | if feature in df.columns: 80 | encoded_df[feature] = df[feature] 81 | if feature in placeholder_df.columns: 82 | encoded_df[feature] = placeholder_df[feature] 83 | # fill all null values 84 | encoded_df.fillna(0, inplace=True) 85 | 86 | return encoded_df 87 | 88 | def normalize_data(df): 89 | val = df.values 90 | min_max_normalizer = preprocessing.MinMaxScaler() 91 | norm_val = min_max_normalizer.fit_transform(val) 92 | df2 = pd.DataFrame(norm_val) 93 | 94 | return df2 95 | 96 | def apply_pre_processing(data): 97 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 98 | encoded = encode_features(data, features_to_encode) 99 | processed_data = normalize_data(encoded) 100 | return processed_data # Please note this is fabricated inference data, so just taking a small sample size 101 | 102 | processed_inference_data = apply_pre_processing(inference_data) 103 | processed_inference_data 104 | 105 | 106 | # ### Load Saved Model 107 | 108 | # %% 109 | 110 | 111 | model = joblib.load('aditya_model1_adaboost.joblib') 112 | model 113 | 114 | 115 | # ### Prediction on inference data 116 | 117 | # %% 118 | 119 | 120 | model.predict(processed_inference_data) 121 | 122 | 123 | # ### Scoring check on prediction 124 | 125 | # %% 126 | 127 | 128 | from sklearn.metrics import accuracy_score 129 | accuracy_score(labels[-20:], model.predict(processed_inference_data)) 130 | 131 | 132 | # %% 133 | 134 | 135 | 136 | 137 | -------------------------------------------------------------------------------- /code documentation/Heart Disease Inference.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | # %% 4 | 5 | # ## Heart Disease Classification 6 | # 7 | # In this notebook, we will try to look at just the inference part of the heart disease classification solution 8 | 9 | # ### Import Modules 10 | 11 | # %% 12 | 13 | 14 | import pandas as pd 15 | import numpy as np 16 | from sklearn import preprocessing 17 | import joblib 18 | 19 | 20 | # ### Get Inference Data 21 | 22 | # %% 23 | 24 | 25 | # in real-time use cases, this method should be replaced with live flowing data 26 | def get_inference_data(): 27 | data = pd.read_csv("Data/heart.csv") 28 | data.drop_duplicates(subset=None, inplace=True) 29 | data.duplicated().any() 30 | inference_df = data.sample(frac=1, random_state = 2) 31 | inference_df = inference_df.tail(20) 32 | return inference_df[inference_df.columns.drop('target')], inference_df['target'] 33 | 34 | inference_data, labels = get_inference_data() 35 | 36 | 37 | # %% 38 | 39 | 40 | inference_data.columns 41 | 42 | 43 | # %% 44 | 45 | 46 | inference_data.head() 47 | 48 | 49 | # ### Apply Same Pre-processing 50 | 51 | # %% 52 | 53 | 54 | # apply same pre-processing and feature engineering techniques as applied during the training process 55 | def encode_features(df, features): 56 | ''' 57 | Method for one-hot encoding all selected categorical fields 58 | ''' 59 | # Implement these steps to prevent dimension mismatch during inference 60 | encoded_df = pd.DataFrame(columns= ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 61 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 62 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 63 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 64 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2']) 65 | placeholder_df = pd.DataFrame() 66 | 67 | # One-Hot Encoding using get_dummies for the specified categorical features 68 | for f in features: 69 | if(f in df.columns): 70 | encoded = pd.get_dummies(df[f]) 71 | encoded = encoded.add_prefix(f + '_') 72 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 73 | else: 74 | print('Feature not found') 75 | return df 76 | 77 | # Implement these steps to prevent dimension mismatch during inference 78 | for feature in encoded_df.columns: 79 | if feature in df.columns: 80 | encoded_df[feature] = df[feature] 81 | if feature in placeholder_df.columns: 82 | encoded_df[feature] = placeholder_df[feature] 83 | # fill all null values 84 | encoded_df.fillna(0, inplace=True) 85 | 86 | return encoded_df 87 | 88 | def normalize_data(df): 89 | val = df.values 90 | min_max_normalizer = preprocessing.MinMaxScaler() 91 | norm_val = min_max_normalizer.fit_transform(val) 92 | df2 = pd.DataFrame(norm_val) 93 | 94 | return df2 95 | 96 | def apply_pre_processing(data): 97 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 98 | encoded = encode_features(data, features_to_encode) 99 | processed_data = normalize_data(encoded) 100 | return processed_data # Please note this is fabricated inference data, so just taking a small sample size 101 | 102 | processed_inference_data = apply_pre_processing(inference_data) 103 | processed_inference_data 104 | 105 | 106 | # ### Load Saved Model 107 | 108 | # %% 109 | 110 | 111 | model = joblib.load('aditya_model1_adaboost.joblib') 112 | model 113 | 114 | 115 | # ### Prediction on inference data 116 | 117 | # %% 118 | 119 | 120 | model.predict(processed_inference_data) 121 | 122 | 123 | # ### Scoring check on prediction 124 | 125 | # %% 126 | 127 | 128 | from sklearn.metrics import accuracy_score 129 | accuracy_score(labels[-20:], model.predict(processed_inference_data)) 130 | 131 | 132 | # %% 133 | 134 | 135 | 136 | 137 | -------------------------------------------------------------------------------- /code linting/Heart Disease Inference.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Classification 5 | # 6 | # In this notebook, we will try to look at just the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | 10 | # In[20]: 11 | 12 | 13 | import pandas as pd 14 | import numpy as np 15 | from sklearn import preprocessing 16 | import joblib 17 | 18 | 19 | # ### Get Inference Data 20 | 21 | # In[79]: 22 | 23 | 24 | # in real-time use cases, this method should be replaced with live flowing data 25 | def get_inference_data(): 26 | data = pd.read_csv("Data/heart.csv") 27 | data.drop_duplicates(subset=None, inplace=True) 28 | data.duplicated().any() 29 | inference_df = data.sample(frac=1, random_state = 2) 30 | inference_df = inference_df.tail(20) 31 | return inference_df[inference_df.columns.drop('target')], inference_df['target'] 32 | 33 | inference_data, labels = get_inference_data() 34 | 35 | 36 | # In[84]: 37 | 38 | 39 | inference_data.columns 40 | 41 | 42 | # In[85]: 43 | 44 | 45 | inference_data.head() 46 | 47 | 48 | # ### Apply Same Pre-processing 49 | 50 | # In[80]: 51 | 52 | 53 | # apply same pre-processing and feature engineering techniques as applied during the training process 54 | def encode_features(df, features): 55 | ''' 56 | Method for one-hot encoding all selected categorical fields 57 | ''' 58 | # Implement these steps to prevent dimension mismatch during inference 59 | encoded_df = pd.DataFrame(columns= ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar', 60 | 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1', 61 | 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2', 62 | 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2', 63 | 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2']) 64 | placeholder_df = pd.DataFrame() 65 | 66 | # One-Hot Encoding using get_dummies for the specified categorical features 67 | for f in features: 68 | if(f in df.columns): 69 | encoded = pd.get_dummies(df[f]) 70 | encoded = encoded.add_prefix(f + '_') 71 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 72 | else: 73 | print('Feature not found') 74 | return df 75 | 76 | # Implement these steps to prevent dimension mismatch during inference 77 | for feature in encoded_df.columns: 78 | if feature in df.columns: 79 | encoded_df[feature] = df[feature] 80 | if feature in placeholder_df.columns: 81 | encoded_df[feature] = placeholder_df[feature] 82 | # fill all null values 83 | encoded_df.fillna(0, inplace=True) 84 | 85 | return encoded_df 86 | 87 | def normalize_data(df): 88 | val = df.values 89 | min_max_normalizer = preprocessing.MinMaxScaler() 90 | norm_val = min_max_normalizer.fit_transform(val) 91 | df2 = pd.DataFrame(norm_val) 92 | 93 | return df2 94 | 95 | def apply_pre_processing(data): 96 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 97 | encoded = encode_features(data, features_to_encode) 98 | processed_data = normalize_data(encoded) 99 | return processed_data # Please note this is fabricated inference data, so just taking a small sample size 100 | 101 | processed_inference_data = apply_pre_processing(inference_data) 102 | processed_inference_data 103 | 104 | 105 | # ### Load Saved Model 106 | 107 | # In[81]: 108 | 109 | 110 | model = joblib.load('aditya_model1_adaboost.joblib') 111 | model 112 | 113 | 114 | # ### Prediction on inference data 115 | 116 | # In[82]: 117 | 118 | 119 | model.predict(processed_inference_data) 120 | 121 | 122 | # ### Scoring check on prediction 123 | 124 | # In[83]: 125 | 126 | 127 | from sklearn.metrics import accuracy_score 128 | accuracy_score(labels[-20:], model.predict(processed_inference_data)) 129 | 130 | 131 | # In[ ]: 132 | 133 | 134 | 135 | 136 | -------------------------------------------------------------------------------- /uci_heart_disease/Heart Disease Inference Modularized.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## Heart Disease Inference Modularized\n", 8 | "\n", 9 | "In this notebook, we will try to look at just the inference part of the heart disease classification solution\n", 10 | "\n", 11 | "The process of applying the same transformations like data pre-processing, feature engineering etc. which was applied during the training process, and then applying the trained ML model to generate predictions is termed as the inference process." 12 | ] 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "### Import Modules" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 1, 24 | "metadata": {}, 25 | "outputs": [], 26 | "source": [ 27 | "import warnings\n", 28 | "warnings.filterwarnings(\"ignore\")\n", 29 | "import pandas as pd\n", 30 | "import numpy as np\n", 31 | "import joblib\n", 32 | "from sklearn.metrics import accuracy_score\n", 33 | "from utils import *\n", 34 | "from constants import *" 35 | ] 36 | }, 37 | { 38 | "cell_type": "markdown", 39 | "metadata": {}, 40 | "source": [ 41 | "### Get Inference Data" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 2, 47 | "metadata": {}, 48 | "outputs": [], 49 | "source": [ 50 | "# in real-time use cases, this code should be replaced with live flowing data\n", 51 | "inference_data, labels = get_inference_data()" 52 | ] 53 | }, 54 | { 55 | "cell_type": "markdown", 56 | "metadata": {}, 57 | "source": [ 58 | "### Apply Same Pre-processing" 59 | ] 60 | }, 61 | { 62 | "cell_type": "code", 63 | "execution_count": 4, 64 | "metadata": {}, 65 | "outputs": [], 66 | "source": [ 67 | "processed_inference_data = apply_pre_processing(inference_data)" 68 | ] 69 | }, 70 | { 71 | "cell_type": "markdown", 72 | "metadata": {}, 73 | "source": [ 74 | "### Load Saved Model" 75 | ] 76 | }, 77 | { 78 | "cell_type": "code", 79 | "execution_count": 5, 80 | "metadata": {}, 81 | "outputs": [], 82 | "source": [ 83 | "model = joblib.load(MODEL_NAME)" 84 | ] 85 | }, 86 | { 87 | "cell_type": "markdown", 88 | "metadata": {}, 89 | "source": [ 90 | "### Prediction on inference data" 91 | ] 92 | }, 93 | { 94 | "cell_type": "code", 95 | "execution_count": 6, 96 | "metadata": {}, 97 | "outputs": [ 98 | { 99 | "data": { 100 | "text/plain": [ 101 | "array([1., 1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1.,\n", 102 | " 1., 1., 0.])" 103 | ] 104 | }, 105 | "execution_count": 6, 106 | "metadata": {}, 107 | "output_type": "execute_result" 108 | } 109 | ], 110 | "source": [ 111 | "model.predict(processed_inference_data)" 112 | ] 113 | }, 114 | { 115 | "cell_type": "markdown", 116 | "metadata": {}, 117 | "source": [ 118 | "### Scoring check on prediction" 119 | ] 120 | }, 121 | { 122 | "cell_type": "code", 123 | "execution_count": 7, 124 | "metadata": {}, 125 | "outputs": [ 126 | { 127 | "data": { 128 | "text/plain": [ 129 | "0.85" 130 | ] 131 | }, 132 | "execution_count": 7, 133 | "metadata": {}, 134 | "output_type": "execute_result" 135 | } 136 | ], 137 | "source": [ 138 | "accuracy_score(labels, model.predict(processed_inference_data))" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": {}, 145 | "outputs": [], 146 | "source": [] 147 | } 148 | ], 149 | "metadata": { 150 | "kernelspec": { 151 | "display_name": "Python 3", 152 | "language": "python", 153 | "name": "python3" 154 | }, 155 | "language_info": { 156 | "codemirror_mode": { 157 | "name": "ipython", 158 | "version": 3 159 | }, 160 | "file_extension": ".py", 161 | "mimetype": "text/x-python", 162 | "name": "python", 163 | "nbconvert_exporter": "python", 164 | "pygments_lexer": "ipython3", 165 | "version": "3.7.7" 166 | } 167 | }, 168 | "nbformat": 4, 169 | "nbformat_minor": 5 170 | } 171 | -------------------------------------------------------------------------------- /code documentation/Heart Disease Inference Modularized.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## Heart Disease Inference Modularized\n", 8 | "\n", 9 | "In this notebook, we will try to look at just the inference part of the heart disease classification solution\n", 10 | "\n", 11 | "The process of applying the same transformations like data pre-processing, feature engineering etc. which was applied during the training process, and then applying the trained ML model to generate predictions is termed as the inference process." 12 | ] 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "### Import Modules" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 12, 24 | "metadata": {}, 25 | "outputs": [], 26 | "source": [ 27 | "import warnings\n", 28 | "warnings.filterwarnings(\"ignore\")\n", 29 | "import pandas as pd\n", 30 | "import numpy as np\n", 31 | "import joblib\n", 32 | "from sklearn.metrics import accuracy_score\n", 33 | "from utils import *\n", 34 | "from constants import *" 35 | ] 36 | }, 37 | { 38 | "cell_type": "markdown", 39 | "metadata": {}, 40 | "source": [ 41 | "### Get Inference Data" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 3, 47 | "metadata": {}, 48 | "outputs": [], 49 | "source": [ 50 | "# in real-time use cases, this code should be replaced with live flowing data\n", 51 | "inference_data, labels = get_inference_data()" 52 | ] 53 | }, 54 | { 55 | "cell_type": "markdown", 56 | "metadata": {}, 57 | "source": [ 58 | "### Apply Same Pre-processing" 59 | ] 60 | }, 61 | { 62 | "cell_type": "code", 63 | "execution_count": 7, 64 | "metadata": {}, 65 | "outputs": [], 66 | "source": [ 67 | "processed_inference_data = apply_pre_processing(inference_data)" 68 | ] 69 | }, 70 | { 71 | "cell_type": "markdown", 72 | "metadata": {}, 73 | "source": [ 74 | "### Load Saved Model" 75 | ] 76 | }, 77 | { 78 | "cell_type": "code", 79 | "execution_count": 10, 80 | "metadata": {}, 81 | "outputs": [], 82 | "source": [ 83 | "model = joblib.load(MODEL_NAME)" 84 | ] 85 | }, 86 | { 87 | "cell_type": "markdown", 88 | "metadata": {}, 89 | "source": [ 90 | "### Prediction on inference data" 91 | ] 92 | }, 93 | { 94 | "cell_type": "code", 95 | "execution_count": 11, 96 | "metadata": {}, 97 | "outputs": [ 98 | { 99 | "data": { 100 | "text/plain": [ 101 | "array([1., 1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1.,\n", 102 | " 1., 1., 0.])" 103 | ] 104 | }, 105 | "execution_count": 11, 106 | "metadata": {}, 107 | "output_type": "execute_result" 108 | } 109 | ], 110 | "source": [ 111 | "model.predict(processed_inference_data)" 112 | ] 113 | }, 114 | { 115 | "cell_type": "markdown", 116 | "metadata": {}, 117 | "source": [ 118 | "### Scoring check on prediction" 119 | ] 120 | }, 121 | { 122 | "cell_type": "code", 123 | "execution_count": 13, 124 | "metadata": {}, 125 | "outputs": [ 126 | { 127 | "data": { 128 | "text/plain": [ 129 | "0.85" 130 | ] 131 | }, 132 | "execution_count": 13, 133 | "metadata": {}, 134 | "output_type": "execute_result" 135 | } 136 | ], 137 | "source": [ 138 | "accuracy_score(labels, model.predict(processed_inference_data))" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": {}, 145 | "outputs": [], 146 | "source": [] 147 | } 148 | ], 149 | "metadata": { 150 | "kernelspec": { 151 | "display_name": "Python 3", 152 | "language": "python", 153 | "name": "python3" 154 | }, 155 | "language_info": { 156 | "codemirror_mode": { 157 | "name": "ipython", 158 | "version": 3 159 | }, 160 | "file_extension": ".py", 161 | "mimetype": "text/x-python", 162 | "name": "python", 163 | "nbconvert_exporter": "python", 164 | "pygments_lexer": "ipython3", 165 | "version": "3.7.7" 166 | } 167 | }, 168 | "nbformat": 4, 169 | "nbformat_minor": 5 170 | } 171 | -------------------------------------------------------------------------------- /unit testing/Heart Disease Inference Modularized.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## Heart Disease Inference Modularized\n", 8 | "\n", 9 | "In this notebook, we will try to look at just the inference part of the heart disease classification solution\n", 10 | "\n", 11 | "The process of applying the same transformations like data pre-processing, feature engineering etc. which was applied during the training process, and then applying the trained ML model to generate predictions is termed as the inference process." 12 | ] 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "### Import Modules" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 1, 24 | "metadata": {}, 25 | "outputs": [], 26 | "source": [ 27 | "import warnings\n", 28 | "warnings.filterwarnings(\"ignore\")\n", 29 | "import pandas as pd\n", 30 | "import numpy as np\n", 31 | "import joblib\n", 32 | "from sklearn.metrics import accuracy_score\n", 33 | "from utils import *\n", 34 | "from constants import *" 35 | ] 36 | }, 37 | { 38 | "cell_type": "markdown", 39 | "metadata": {}, 40 | "source": [ 41 | "### Get Inference Data" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 2, 47 | "metadata": {}, 48 | "outputs": [], 49 | "source": [ 50 | "# in real-time use cases, this code should be replaced with live flowing data\n", 51 | "# use get_inference_data() from utils.py to fetch inference data\n", 52 | "inference_data, labels = get_inference_data()" 53 | ] 54 | }, 55 | { 56 | "cell_type": "markdown", 57 | "metadata": {}, 58 | "source": [ 59 | "### Apply Same Pre-processing" 60 | ] 61 | }, 62 | { 63 | "cell_type": "code", 64 | "execution_count": 3, 65 | "metadata": {}, 66 | "outputs": [], 67 | "source": [ 68 | "# use apply_pre_processing() from utils.py \n", 69 | "# to apply necessary preprocessing as applied for training data\n", 70 | "processed_inference_data = apply_pre_processing(inference_data)" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "### Load Saved Model" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": 10, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# use MODEL_NAME from constants.py\n", 87 | "model = joblib.load(MODEL_NAME)" 88 | ] 89 | }, 90 | { 91 | "cell_type": "markdown", 92 | "metadata": {}, 93 | "source": [ 94 | "### Prediction on inference data" 95 | ] 96 | }, 97 | { 98 | "cell_type": "code", 99 | "execution_count": 11, 100 | "metadata": {}, 101 | "outputs": [ 102 | { 103 | "data": { 104 | "text/plain": [ 105 | "array([1., 1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1.,\n", 106 | " 1., 1., 0.])" 107 | ] 108 | }, 109 | "execution_count": 11, 110 | "metadata": {}, 111 | "output_type": "execute_result" 112 | } 113 | ], 114 | "source": [ 115 | "# perform model prediction on inference data\n", 116 | "model.predict(processed_inference_data)" 117 | ] 118 | }, 119 | { 120 | "cell_type": "markdown", 121 | "metadata": {}, 122 | "source": [ 123 | "### Scoring check on prediction" 124 | ] 125 | }, 126 | { 127 | "cell_type": "code", 128 | "execution_count": 13, 129 | "metadata": {}, 130 | "outputs": [ 131 | { 132 | "data": { 133 | "text/plain": [ 134 | "0.85" 135 | ] 136 | }, 137 | "execution_count": 13, 138 | "metadata": {}, 139 | "output_type": "execute_result" 140 | } 141 | ], 142 | "source": [ 143 | "# check inference accuracy\n", 144 | "accuracy_score(labels, model.predict(processed_inference_data))" 145 | ] 146 | }, 147 | { 148 | "cell_type": "code", 149 | "execution_count": null, 150 | "metadata": {}, 151 | "outputs": [], 152 | "source": [] 153 | } 154 | ], 155 | "metadata": { 156 | "kernelspec": { 157 | "display_name": "Python 3", 158 | "language": "python", 159 | "name": "python3" 160 | }, 161 | "language_info": { 162 | "codemirror_mode": { 163 | "name": "ipython", 164 | "version": 3 165 | }, 166 | "file_extension": ".py", 167 | "mimetype": "text/x-python", 168 | "name": "python", 169 | "nbconvert_exporter": "python", 170 | "pygments_lexer": "ipython3", 171 | "version": "3.7.7" 172 | } 173 | }, 174 | "nbformat": 4, 175 | "nbformat_minor": 5 176 | } 177 | -------------------------------------------------------------------------------- /python scripting/Heart Disease Inference Modularized.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## Heart Disease Inference Modularized\n", 8 | "\n", 9 | "In this notebook, we will try to look at just the inference part of the heart disease classification solution\n", 10 | "\n", 11 | "The process of applying the same transformations like data pre-processing, feature engineering etc. which was applied during the training process, and then applying the trained ML model to generate predictions is termed as the inference process." 12 | ] 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "### Import Modules" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 1, 24 | "metadata": {}, 25 | "outputs": [], 26 | "source": [ 27 | "import warnings\n", 28 | "warnings.filterwarnings(\"ignore\")\n", 29 | "import pandas as pd\n", 30 | "import numpy as np\n", 31 | "import joblib\n", 32 | "from sklearn.metrics import accuracy_score\n", 33 | "from utils import *\n", 34 | "from constants import *" 35 | ] 36 | }, 37 | { 38 | "cell_type": "markdown", 39 | "metadata": {}, 40 | "source": [ 41 | "### Get Inference Data" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 2, 47 | "metadata": {}, 48 | "outputs": [], 49 | "source": [ 50 | "# in real-time use cases, this code should be replaced with live flowing data\n", 51 | "# use get_inference_data() from utils.py to fetch inference data\n", 52 | "inference_data, labels = get_inference_data()" 53 | ] 54 | }, 55 | { 56 | "cell_type": "markdown", 57 | "metadata": {}, 58 | "source": [ 59 | "### Apply Same Pre-processing" 60 | ] 61 | }, 62 | { 63 | "cell_type": "code", 64 | "execution_count": 3, 65 | "metadata": {}, 66 | "outputs": [], 67 | "source": [ 68 | "# use apply_pre_processing() from utils.py \n", 69 | "# to apply necessary preprocessing as applied for training data\n", 70 | "processed_inference_data = apply_pre_processing(inference_data)" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "### Load Saved Model" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": 10, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# use MODEL_NAME from constants.py\n", 87 | "model = joblib.load(MODEL_NAME)" 88 | ] 89 | }, 90 | { 91 | "cell_type": "markdown", 92 | "metadata": {}, 93 | "source": [ 94 | "### Prediction on inference data" 95 | ] 96 | }, 97 | { 98 | "cell_type": "code", 99 | "execution_count": 11, 100 | "metadata": {}, 101 | "outputs": [ 102 | { 103 | "data": { 104 | "text/plain": [ 105 | "array([1., 1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1.,\n", 106 | " 1., 1., 0.])" 107 | ] 108 | }, 109 | "execution_count": 11, 110 | "metadata": {}, 111 | "output_type": "execute_result" 112 | } 113 | ], 114 | "source": [ 115 | "# perform model prediction on inference data\n", 116 | "model.predict(processed_inference_data)" 117 | ] 118 | }, 119 | { 120 | "cell_type": "markdown", 121 | "metadata": {}, 122 | "source": [ 123 | "### Scoring check on prediction" 124 | ] 125 | }, 126 | { 127 | "cell_type": "code", 128 | "execution_count": 13, 129 | "metadata": {}, 130 | "outputs": [ 131 | { 132 | "data": { 133 | "text/plain": [ 134 | "0.85" 135 | ] 136 | }, 137 | "execution_count": 13, 138 | "metadata": {}, 139 | "output_type": "execute_result" 140 | } 141 | ], 142 | "source": [ 143 | "# check inference accuracy\n", 144 | "accuracy_score(labels, model.predict(processed_inference_data))" 145 | ] 146 | }, 147 | { 148 | "cell_type": "code", 149 | "execution_count": null, 150 | "metadata": {}, 151 | "outputs": [], 152 | "source": [] 153 | } 154 | ], 155 | "metadata": { 156 | "kernelspec": { 157 | "display_name": "Python 3", 158 | "language": "python", 159 | "name": "python3" 160 | }, 161 | "language_info": { 162 | "codemirror_mode": { 163 | "name": "ipython", 164 | "version": 3 165 | }, 166 | "file_extension": ".py", 167 | "mimetype": "text/x-python", 168 | "name": "python", 169 | "nbconvert_exporter": "python", 170 | "pygments_lexer": "ipython3", 171 | "version": "3.7.7" 172 | } 173 | }, 174 | "nbformat": 4, 175 | "nbformat_minor": 5 176 | } 177 | -------------------------------------------------------------------------------- /code documentation/Corrected/Heart Disease Inference Modularized.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## Heart Disease Inference Modularized\n", 8 | "\n", 9 | "In this notebook, we will try to look at just the inference part of the heart disease classification solution\n", 10 | "\n", 11 | "The process of applying the same transformations like data pre-processing, feature engineering etc. which was applied during the training process, and then applying the trained ML model to generate predictions is termed as the inference process." 12 | ] 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "### Import Modules" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 12, 24 | "metadata": {}, 25 | "outputs": [], 26 | "source": [ 27 | "import warnings\n", 28 | "warnings.filterwarnings(\"ignore\")\n", 29 | "import pandas as pd\n", 30 | "import numpy as np\n", 31 | "import joblib\n", 32 | "from sklearn.metrics import accuracy_score\n", 33 | "from utils import *\n", 34 | "from constants import *" 35 | ] 36 | }, 37 | { 38 | "cell_type": "markdown", 39 | "metadata": {}, 40 | "source": [ 41 | "### Get Inference Data" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 3, 47 | "metadata": {}, 48 | "outputs": [], 49 | "source": [ 50 | "# in real-time use cases, this code should be replaced with live flowing data\n", 51 | "# use get_inference_data() from utils.py to fetch inference data\n", 52 | "inference_data, labels = get_inference_data()" 53 | ] 54 | }, 55 | { 56 | "cell_type": "markdown", 57 | "metadata": {}, 58 | "source": [ 59 | "### Apply Same Pre-processing" 60 | ] 61 | }, 62 | { 63 | "cell_type": "code", 64 | "execution_count": 7, 65 | "metadata": {}, 66 | "outputs": [], 67 | "source": [ 68 | "# use apply_pre_processing() from utils.py \n", 69 | "# to apply necessary preprocessing as applied for training data\n", 70 | "processed_inference_data = apply_pre_processing(inference_data)" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "### Load Saved Model" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": 10, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# use MODEL_NAME from constants.py\n", 87 | "model = joblib.load(MODEL_NAME)" 88 | ] 89 | }, 90 | { 91 | "cell_type": "markdown", 92 | "metadata": {}, 93 | "source": [ 94 | "### Prediction on inference data" 95 | ] 96 | }, 97 | { 98 | "cell_type": "code", 99 | "execution_count": 11, 100 | "metadata": {}, 101 | "outputs": [ 102 | { 103 | "data": { 104 | "text/plain": [ 105 | "array([1., 1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1.,\n", 106 | " 1., 1., 0.])" 107 | ] 108 | }, 109 | "execution_count": 11, 110 | "metadata": {}, 111 | "output_type": "execute_result" 112 | } 113 | ], 114 | "source": [ 115 | "# perform model prediction on inference data\n", 116 | "model.predict(processed_inference_data)" 117 | ] 118 | }, 119 | { 120 | "cell_type": "markdown", 121 | "metadata": {}, 122 | "source": [ 123 | "### Scoring check on prediction" 124 | ] 125 | }, 126 | { 127 | "cell_type": "code", 128 | "execution_count": 13, 129 | "metadata": {}, 130 | "outputs": [ 131 | { 132 | "data": { 133 | "text/plain": [ 134 | "0.85" 135 | ] 136 | }, 137 | "execution_count": 13, 138 | "metadata": {}, 139 | "output_type": "execute_result" 140 | } 141 | ], 142 | "source": [ 143 | "# check inference accuracy\n", 144 | "accuracy_score(labels, model.predict(processed_inference_data))" 145 | ] 146 | }, 147 | { 148 | "cell_type": "code", 149 | "execution_count": null, 150 | "metadata": {}, 151 | "outputs": [], 152 | "source": [] 153 | } 154 | ], 155 | "metadata": { 156 | "kernelspec": { 157 | "display_name": "Python 3", 158 | "language": "python", 159 | "name": "python3" 160 | }, 161 | "language_info": { 162 | "codemirror_mode": { 163 | "name": "ipython", 164 | "version": 3 165 | }, 166 | "file_extension": ".py", 167 | "mimetype": "text/x-python", 168 | "name": "python", 169 | "nbconvert_exporter": "python", 170 | "pygments_lexer": "ipython3", 171 | "version": "3.7.7" 172 | } 173 | }, 174 | "nbformat": 4, 175 | "nbformat_minor": 5 176 | } 177 | -------------------------------------------------------------------------------- /exception handling and logging/Heart Disease Inference Modularized.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## Heart Disease Inference Modularized\n", 8 | "\n", 9 | "In this notebook, we will try to look at just the inference part of the heart disease classification solution\n", 10 | "\n", 11 | "The process of applying the same transformations like data pre-processing, feature engineering etc. which was applied during the training process, and then applying the trained ML model to generate predictions is termed as the inference process." 12 | ] 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "### Import Modules" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 1, 24 | "metadata": {}, 25 | "outputs": [], 26 | "source": [ 27 | "import warnings\n", 28 | "warnings.filterwarnings(\"ignore\")\n", 29 | "import pandas as pd\n", 30 | "import numpy as np\n", 31 | "import joblib\n", 32 | "from sklearn.metrics import accuracy_score\n", 33 | "from utils import *\n", 34 | "from constants import *" 35 | ] 36 | }, 37 | { 38 | "cell_type": "markdown", 39 | "metadata": {}, 40 | "source": [ 41 | "### Get Inference Data" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": 2, 47 | "metadata": {}, 48 | "outputs": [], 49 | "source": [ 50 | "# in real-time use cases, this code should be replaced with live flowing data\n", 51 | "# use get_inference_data() from utils.py to fetch inference data\n", 52 | "inference_data, labels = get_inference_data()" 53 | ] 54 | }, 55 | { 56 | "cell_type": "markdown", 57 | "metadata": {}, 58 | "source": [ 59 | "### Apply Same Pre-processing" 60 | ] 61 | }, 62 | { 63 | "cell_type": "code", 64 | "execution_count": 3, 65 | "metadata": {}, 66 | "outputs": [], 67 | "source": [ 68 | "# use apply_pre_processing() from utils.py \n", 69 | "# to apply necessary preprocessing as applied for training data\n", 70 | "processed_inference_data = apply_pre_processing(inference_data)" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "### Load Saved Model" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": 10, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# use MODEL_NAME from constants.py\n", 87 | "model = joblib.load(MODEL_NAME)" 88 | ] 89 | }, 90 | { 91 | "cell_type": "markdown", 92 | "metadata": {}, 93 | "source": [ 94 | "### Prediction on inference data" 95 | ] 96 | }, 97 | { 98 | "cell_type": "code", 99 | "execution_count": 11, 100 | "metadata": {}, 101 | "outputs": [ 102 | { 103 | "data": { 104 | "text/plain": [ 105 | "array([1., 1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1.,\n", 106 | " 1., 1., 0.])" 107 | ] 108 | }, 109 | "execution_count": 11, 110 | "metadata": {}, 111 | "output_type": "execute_result" 112 | } 113 | ], 114 | "source": [ 115 | "# perform model prediction on inference data\n", 116 | "model.predict(processed_inference_data)" 117 | ] 118 | }, 119 | { 120 | "cell_type": "markdown", 121 | "metadata": {}, 122 | "source": [ 123 | "### Scoring check on prediction" 124 | ] 125 | }, 126 | { 127 | "cell_type": "code", 128 | "execution_count": 13, 129 | "metadata": {}, 130 | "outputs": [ 131 | { 132 | "data": { 133 | "text/plain": [ 134 | "0.85" 135 | ] 136 | }, 137 | "execution_count": 13, 138 | "metadata": {}, 139 | "output_type": "execute_result" 140 | } 141 | ], 142 | "source": [ 143 | "# check inference accuracy\n", 144 | "accuracy_score(labels, model.predict(processed_inference_data))" 145 | ] 146 | }, 147 | { 148 | "cell_type": "code", 149 | "execution_count": null, 150 | "metadata": {}, 151 | "outputs": [], 152 | "source": [] 153 | } 154 | ], 155 | "metadata": { 156 | "kernelspec": { 157 | "display_name": "Python 3", 158 | "language": "python", 159 | "name": "python3" 160 | }, 161 | "language_info": { 162 | "codemirror_mode": { 163 | "name": "ipython", 164 | "version": 3 165 | }, 166 | "file_extension": ".py", 167 | "mimetype": "text/x-python", 168 | "name": "python", 169 | "nbconvert_exporter": "python", 170 | "pygments_lexer": "ipython3", 171 | "version": "3.7.7" 172 | } 173 | }, 174 | "nbformat": 4, 175 | "nbformat_minor": 5 176 | } 177 | -------------------------------------------------------------------------------- /code linting/Corrected/Heart Disease Inference.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Classification 5 | # In this script, we will try to look at 6 | # the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | import pandas as pd 10 | import numpy as np 11 | from sklearn import preprocessing 12 | import joblib 13 | from sklearn.metrics import accuracy_score 14 | 15 | 16 | # ### Get Inference Data 17 | # in real-time use cases, this method should be replaced with live flowing data 18 | def get_inference_data(): 19 | ''' 20 | Method for loading inference data 21 | Example usage: inference_data, labels = get_inference_data() 22 | ''' 23 | data = pd.read_csv("Data/heart.csv") 24 | data.drop_duplicates(subset=None, inplace=True) 25 | data.duplicated().any() 26 | df = data.sample(frac=1, random_state=2) 27 | # Taking last 20 records as an example only 28 | df = df.tail(20) 29 | return df[df.columns.drop('target')], df['target'] 30 | 31 | 32 | inference_data, labels = get_inference_data() 33 | 34 | # ### Apply Same Pre-processing 35 | 36 | # apply same pre-processing and feature engineering techniques 37 | # as applied during the training process 38 | 39 | 40 | def encode_features(df, features): 41 | ''' 42 | Method for one-hot encoding all selected categorical fields 43 | Input: The method takes pandas dataframe and 44 | list of the feature names as input 45 | Output: Returns a dataframe with one-hot encoded features 46 | Example usage: 47 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 48 | ''' 49 | # Implement these steps to prevent dimension mismatch during inference 50 | encoded_df = pd.DataFrame(columns=['age', 'sex', 'resting_bp', 51 | 'cholestoral', 'fasting_blood_sugar', 52 | 'max_hr', 'exang', 'oldpeak', 53 | 'num_major_vessels', 'thal_0', 'thal_1', 54 | 'thal_2', 'thal_3', 'slope_0', 55 | 'slope_1', 'slope_2', 56 | 'chest_pain_type_0', 57 | 'chest_pain_type_1', 58 | 'chest_pain_type_2', 59 | 'chest_pain_type_3', 'restecg_0', 60 | 'restecg_1', 'restecg_2']) 61 | placeholder_df = pd.DataFrame() 62 | 63 | # One-Hot Encoding using get_dummies for the specified categorical features 64 | for f in features: 65 | if(f in df.columns): 66 | encoded = pd.get_dummies(df[f]) 67 | encoded = encoded.add_prefix(f + '_') 68 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 69 | else: 70 | print('Feature not found') 71 | return df 72 | 73 | # Implement these steps to prevent dimension mismatch during inference 74 | for feature in encoded_df.columns: 75 | if feature in df.columns: 76 | encoded_df[feature] = df[feature] 77 | if feature in placeholder_df.columns: 78 | encoded_df[feature] = placeholder_df[feature] 79 | # fill all null values 80 | encoded_df.fillna(0, inplace=True) 81 | 82 | return encoded_df 83 | 84 | 85 | def normalize_data(df): 86 | ''' 87 | Normalize data using Min-Max Scaler 88 | Input: The method takes pandas dataframe as input 89 | Output: Returns a dataframe with normalized features 90 | Example usage: 91 | normalized_df = normalize_data(df) 92 | ''' 93 | val = df.values 94 | min_max_normalizer = preprocessing.MinMaxScaler() 95 | norm_val = min_max_normalizer.fit_transform(val) 96 | df2 = pd.DataFrame(norm_val) 97 | return df2 98 | 99 | 100 | def apply_pre_processing(data): 101 | ''' 102 | Normalize data using Min-Max Scaler 103 | Input: The method takes pandas dataframe as input 104 | Output: Returns a dataframe with normalized features 105 | Example usage: 106 | normalized_df = normalize_data(df) 107 | ''' 108 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 109 | encoded = encode_features(data, features_to_encode) 110 | processed_data = normalize_data(encoded) 111 | # Please note this is fabricated inference data, 112 | # so just taking a small sample size 113 | return processed_data 114 | 115 | 116 | processed_inference_data = apply_pre_processing(inference_data) 117 | 118 | 119 | # ### Load Saved Model 120 | model = joblib.load('aditya_model1_adaboost.joblib') 121 | 122 | 123 | # ### Prediction on inference data 124 | model.predict(processed_inference_data) 125 | 126 | 127 | # ### Scoring check on prediction 128 | accuracy_score(labels[-20:], model.predict(processed_inference_data)) 129 | -------------------------------------------------------------------------------- /code documentation/Corrected/Heart Disease Inference.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Classification 5 | # In this script, we will try to look at 6 | # the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | import pandas as pd 10 | import numpy as np 11 | from sklearn import preprocessing 12 | import joblib 13 | from sklearn.metrics import accuracy_score 14 | 15 | 16 | # ### Get Inference Data 17 | # in real-time use cases, this method should be replaced with live flowing data 18 | def get_inference_data(): 19 | ''' 20 | Method for loading inference data 21 | Example usage: inference_data, labels = get_inference_data() 22 | ''' 23 | data = pd.read_csv("Data/heart.csv") 24 | data.drop_duplicates(subset=None, inplace=True) 25 | data.duplicated().any() 26 | df = data.sample(frac=1, random_state=2) 27 | # Taking last 20 records as an example only 28 | df = df.tail(20) 29 | return df[df.columns.drop('target')], df['target'] 30 | 31 | 32 | inference_data, labels = get_inference_data() 33 | 34 | # ### Apply Same Pre-processing 35 | 36 | # apply same pre-processing and feature engineering techniques 37 | # as applied during the training process 38 | 39 | 40 | def encode_features(df, features): 41 | ''' 42 | Method for one-hot encoding all selected categorical fields 43 | Input: The method takes pandas dataframe and 44 | list of the feature names as input 45 | Output: Returns a dataframe with one-hot encoded features 46 | Example usage: 47 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 48 | ''' 49 | # Implement these steps to prevent dimension mismatch during inference 50 | encoded_df = pd.DataFrame(columns=['age', 'sex', 'resting_bp', 51 | 'cholestoral', 'fasting_blood_sugar', 52 | 'max_hr', 'exang', 'oldpeak', 53 | 'num_major_vessels', 'thal_0', 'thal_1', 54 | 'thal_2', 'thal_3', 'slope_0', 55 | 'slope_1', 'slope_2', 56 | 'chest_pain_type_0', 57 | 'chest_pain_type_1', 58 | 'chest_pain_type_2', 59 | 'chest_pain_type_3', 'restecg_0', 60 | 'restecg_1', 'restecg_2']) 61 | placeholder_df = pd.DataFrame() 62 | 63 | # One-Hot Encoding using get_dummies for the specified categorical features 64 | for f in features: 65 | if(f in df.columns): 66 | encoded = pd.get_dummies(df[f]) 67 | encoded = encoded.add_prefix(f + '_') 68 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 69 | else: 70 | print('Feature not found') 71 | return df 72 | 73 | # Implement these steps to prevent dimension mismatch during inference 74 | for feature in encoded_df.columns: 75 | if feature in df.columns: 76 | encoded_df[feature] = df[feature] 77 | if feature in placeholder_df.columns: 78 | encoded_df[feature] = placeholder_df[feature] 79 | # fill all null values 80 | encoded_df.fillna(0, inplace=True) 81 | 82 | return encoded_df 83 | 84 | 85 | def normalize_data(df): 86 | ''' 87 | Normalize data using Min-Max Scaler 88 | Input: The method takes pandas dataframe as input 89 | Output: Returns a dataframe with normalized features 90 | Example usage: 91 | normalized_df = normalize_data(df) 92 | ''' 93 | val = df.values 94 | min_max_normalizer = preprocessing.MinMaxScaler() 95 | norm_val = min_max_normalizer.fit_transform(val) 96 | df2 = pd.DataFrame(norm_val) 97 | return df2 98 | 99 | 100 | def apply_pre_processing(data): 101 | ''' 102 | Normalize data using Min-Max Scaler 103 | Input: The method takes pandas dataframe as input 104 | Output: Returns a dataframe with normalized features 105 | Example usage: 106 | normalized_df = normalize_data(df) 107 | ''' 108 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 109 | encoded = encode_features(data, features_to_encode) 110 | processed_data = normalize_data(encoded) 111 | # Please note this is fabricated inference data, 112 | # so just taking a small sample size 113 | return processed_data 114 | 115 | 116 | processed_inference_data = apply_pre_processing(inference_data) 117 | 118 | 119 | # ### Load Saved Model 120 | model = joblib.load('aditya_model1_adaboost.joblib') 121 | 122 | 123 | # ### Prediction on inference data 124 | model.predict(processed_inference_data) 125 | 126 | 127 | # ### Scoring check on prediction 128 | accuracy_score(labels[-20:], model.predict(processed_inference_data)) 129 | -------------------------------------------------------------------------------- /unit testing/main.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Classification 5 | # In this script, we will try to look at 6 | # the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | import warnings 10 | warnings.filterwarnings("ignore") 11 | import pandas as pd 12 | import numpy as np 13 | from sklearn import preprocessing 14 | import joblib 15 | from sklearn.metrics import accuracy_score 16 | import argparse 17 | 18 | 19 | # ### Get Inference Data 20 | # in real-time use cases, this method should be replaced with live flowing data 21 | def get_inference_data(): 22 | ''' 23 | Method for loading inference data 24 | Example usage: inference_data, labels = get_inference_data() 25 | ''' 26 | data = pd.read_csv("Data/heart.csv") 27 | data.drop_duplicates(subset=None, inplace=True) 28 | data.duplicated().any() 29 | df = data.sample(frac=1, random_state=2) 30 | # Taking last 20 records as an example only 31 | df = df.tail(20) 32 | return df[df.columns.drop('target')], df['target'] 33 | 34 | 35 | # ### Apply Same Pre-processing 36 | 37 | # apply same pre-processing and feature engineering techniques 38 | # as applied during the training process 39 | 40 | 41 | def encode_features(df, features): 42 | ''' 43 | Method for one-hot encoding all selected categorical fields 44 | Input: The method takes pandas dataframe and 45 | list of the feature names as input 46 | Output: Returns a dataframe with one-hot encoded features 47 | Example usage: 48 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 49 | ''' 50 | # Implement these steps to prevent dimension mismatch during inference 51 | encoded_df = pd.DataFrame(columns=['age', 'sex', 'resting_bp', 52 | 'cholestoral', 'fasting_blood_sugar', 53 | 'max_hr', 'exang', 'oldpeak', 54 | 'num_major_vessels', 'thal_0', 'thal_1', 55 | 'thal_2', 'thal_3', 'slope_0', 56 | 'slope_1', 'slope_2', 57 | 'chest_pain_type_0', 58 | 'chest_pain_type_1', 59 | 'chest_pain_type_2', 60 | 'chest_pain_type_3', 'restecg_0', 61 | 'restecg_1', 'restecg_2']) 62 | placeholder_df = pd.DataFrame() 63 | 64 | # One-Hot Encoding using get_dummies for the specified categorical features 65 | for f in features: 66 | if(f in df.columns): 67 | encoded = pd.get_dummies(df[f]) 68 | encoded = encoded.add_prefix(f + '_') 69 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 70 | else: 71 | print('Feature not found') 72 | return df 73 | 74 | # Implement these steps to prevent dimension mismatch during inference 75 | for feature in encoded_df.columns: 76 | if feature in df.columns: 77 | encoded_df[feature] = df[feature] 78 | if feature in placeholder_df.columns: 79 | encoded_df[feature] = placeholder_df[feature] 80 | # fill all null values 81 | encoded_df.fillna(0, inplace=True) 82 | 83 | return encoded_df 84 | 85 | 86 | def normalize_data(df): 87 | ''' 88 | Normalize data using Min-Max Scaler 89 | Input: The method takes pandas dataframe as input 90 | Output: Returns a dataframe with normalized features 91 | Example usage: 92 | normalized_df = normalize_data(df) 93 | ''' 94 | val = df.values 95 | min_max_normalizer = preprocessing.MinMaxScaler() 96 | norm_val = min_max_normalizer.fit_transform(val) 97 | df2 = pd.DataFrame(norm_val) 98 | return df2 99 | 100 | 101 | def apply_pre_processing(data): 102 | ''' 103 | Normalize data using Min-Max Scaler 104 | Input: The method takes pandas dataframe as input 105 | Output: Returns a dataframe with normalized features 106 | Example usage: 107 | normalized_df = normalize_data(df) 108 | ''' 109 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 110 | encoded = encode_features(data, features_to_encode) 111 | processed_data = normalize_data(encoded) 112 | # Please note this is fabricated inference data, 113 | # so just taking a small sample size 114 | return processed_data 115 | 116 | 117 | # main function - starting point of the code 118 | def main(model_name): 119 | ''' 120 | main function - starting point of the code 121 | ''' 122 | print("Starting execution of the inference code...") 123 | inference_data, labels = get_inference_data() 124 | processed_inference_data = apply_pre_processing(inference_data) 125 | # ### Load Saved Model 126 | model = joblib.load(model_name) 127 | # ### Prediction on inference data 128 | model.predict(processed_inference_data) 129 | # ### Scoring check on prediction 130 | print("Checking inference accuracy:") 131 | print(accuracy_score(labels[-20:], model.predict(processed_inference_data))) 132 | 133 | 134 | if __name__ == "__main__": 135 | parser = argparse.ArgumentParser(description='Running inference pipeline') 136 | parser.add_argument('--model', 137 | default='adaboost', 138 | help='select algorithm: svm or adaboost') 139 | args = parser.parse_args() 140 | if(args.model == 'svm'): 141 | model_name = 'aditya_model2_svm.joblib' 142 | else: 143 | model_name = 'aditya_model1_adaboost.joblib' 144 | main(model_name) 145 | -------------------------------------------------------------------------------- /python scripting/Heart Disease Inference.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Classification 5 | # In this script, we will try to look at 6 | # the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | import warnings 10 | warnings.filterwarnings("ignore") 11 | import pandas as pd 12 | import numpy as np 13 | from sklearn import preprocessing 14 | import joblib 15 | from sklearn.metrics import accuracy_score 16 | import argparse 17 | 18 | 19 | # ### Get Inference Data 20 | # in real-time use cases, this method should be replaced with live flowing data 21 | def get_inference_data(): 22 | ''' 23 | Method for loading inference data 24 | Example usage: inference_data, labels = get_inference_data() 25 | ''' 26 | data = pd.read_csv("Data/heart.csv") 27 | data.drop_duplicates(subset=None, inplace=True) 28 | data.duplicated().any() 29 | df = data.sample(frac=1, random_state=2) 30 | # Taking last 20 records as an example only 31 | df = df.tail(20) 32 | return df[df.columns.drop('target')], df['target'] 33 | 34 | 35 | # ### Apply Same Pre-processing 36 | 37 | # apply same pre-processing and feature engineering techniques 38 | # as applied during the training process 39 | 40 | 41 | def encode_features(df, features): 42 | ''' 43 | Method for one-hot encoding all selected categorical fields 44 | Input: The method takes pandas dataframe and 45 | list of the feature names as input 46 | Output: Returns a dataframe with one-hot encoded features 47 | Example usage: 48 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 49 | ''' 50 | # Implement these steps to prevent dimension mismatch during inference 51 | encoded_df = pd.DataFrame(columns=['age', 'sex', 'resting_bp', 52 | 'cholestoral', 'fasting_blood_sugar', 53 | 'max_hr', 'exang', 'oldpeak', 54 | 'num_major_vessels', 'thal_0', 'thal_1', 55 | 'thal_2', 'thal_3', 'slope_0', 56 | 'slope_1', 'slope_2', 57 | 'chest_pain_type_0', 58 | 'chest_pain_type_1', 59 | 'chest_pain_type_2', 60 | 'chest_pain_type_3', 'restecg_0', 61 | 'restecg_1', 'restecg_2']) 62 | placeholder_df = pd.DataFrame() 63 | 64 | # One-Hot Encoding using get_dummies for the specified categorical features 65 | for f in features: 66 | if(f in df.columns): 67 | encoded = pd.get_dummies(df[f]) 68 | encoded = encoded.add_prefix(f + '_') 69 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 70 | else: 71 | print('Feature not found') 72 | return df 73 | 74 | # Implement these steps to prevent dimension mismatch during inference 75 | for feature in encoded_df.columns: 76 | if feature in df.columns: 77 | encoded_df[feature] = df[feature] 78 | if feature in placeholder_df.columns: 79 | encoded_df[feature] = placeholder_df[feature] 80 | # fill all null values 81 | encoded_df.fillna(0, inplace=True) 82 | 83 | return encoded_df 84 | 85 | 86 | def normalize_data(df): 87 | ''' 88 | Normalize data using Min-Max Scaler 89 | Input: The method takes pandas dataframe as input 90 | Output: Returns a dataframe with normalized features 91 | Example usage: 92 | normalized_df = normalize_data(df) 93 | ''' 94 | val = df.values 95 | min_max_normalizer = preprocessing.MinMaxScaler() 96 | norm_val = min_max_normalizer.fit_transform(val) 97 | df2 = pd.DataFrame(norm_val) 98 | return df2 99 | 100 | 101 | def apply_pre_processing(data): 102 | ''' 103 | Normalize data using Min-Max Scaler 104 | Input: The method takes pandas dataframe as input 105 | Output: Returns a dataframe with normalized features 106 | Example usage: 107 | normalized_df = normalize_data(df) 108 | ''' 109 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 110 | encoded = encode_features(data, features_to_encode) 111 | processed_data = normalize_data(encoded) 112 | # Please note this is fabricated inference data, 113 | # so just taking a small sample size 114 | return processed_data 115 | 116 | 117 | # main function - starting point of the code 118 | def main(model_name): 119 | ''' 120 | main function - starting point of the code 121 | ''' 122 | print("Starting execution of the inference code...") 123 | inference_data, labels = get_inference_data() 124 | processed_inference_data = apply_pre_processing(inference_data) 125 | # ### Load Saved Model 126 | model = joblib.load(model_name) 127 | # ### Prediction on inference data 128 | model.predict(processed_inference_data) 129 | # ### Scoring check on prediction 130 | print("Checking inference accuracy:") 131 | print(accuracy_score(labels[-20:], model.predict(processed_inference_data))) 132 | 133 | 134 | if __name__ == "__main__": 135 | parser = argparse.ArgumentParser(description='Running inference pipeline') 136 | parser.add_argument('--model', 137 | default='adaboost', 138 | help='select algorithm: svm or adaboost') 139 | args = parser.parse_args() 140 | if(args.model == 'svm'): 141 | model_name = 'aditya_model2_svm.joblib' 142 | else: 143 | model_name = 'aditya_model1_adaboost.joblib' 144 | main(model_name) -------------------------------------------------------------------------------- /exception handling and logging/main_old.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | # ## Heart Disease Classification 5 | # In this script, we will try to look at 6 | # the inference part of the heart disease classification solution 7 | 8 | # ### Import Modules 9 | import warnings 10 | warnings.filterwarnings("ignore") 11 | import pandas as pd 12 | import numpy as np 13 | from sklearn import preprocessing 14 | import joblib 15 | from sklearn.metrics import accuracy_score 16 | import argparse 17 | import logging 18 | 19 | 20 | # ### Get Inference Data 21 | # in real-time use cases, this method should be replaced with live flowing data 22 | def get_inference_data(): 23 | ''' 24 | Method for loading inference data 25 | Example usage: inference_data, labels = get_inference_data() 26 | ''' 27 | data = pd.read_csv("Data/heart.csv") 28 | data.drop_duplicates(subset=None, inplace=True) 29 | data.duplicated().any() 30 | df = data.sample(frac=1, random_state=2) 31 | # Taking last 20 records as an example only 32 | df = df.tail(20) 33 | return df[df.columns.drop('target')], df['target'] 34 | 35 | 36 | # ### Apply Same Pre-processing 37 | 38 | # apply same pre-processing and feature engineering techniques 39 | # as applied during the training process 40 | 41 | 42 | def encode_features(df, features): 43 | ''' 44 | Method for one-hot encoding all selected categorical fields 45 | Input: The method takes pandas dataframe and 46 | list of the feature names as input 47 | Output: Returns a dataframe with one-hot encoded features 48 | Example usage: 49 | one_hot_encoded_df = encode_features(dataframe, list_features_to_encode) 50 | ''' 51 | # Implement these steps to prevent dimension mismatch during inference 52 | encoded_df = pd.DataFrame(columns=['age', 'sex', 'resting_bp', 53 | 'cholestoral', 'fasting_blood_sugar', 54 | 'max_hr', 'exang', 'oldpeak', 55 | 'num_major_vessels', 'thal_0', 'thal_1', 56 | 'thal_2', 'thal_3', 'slope_0', 57 | 'slope_1', 'slope_2', 58 | 'chest_pain_type_0', 59 | 'chest_pain_type_1', 60 | 'chest_pain_type_2', 61 | 'chest_pain_type_3', 'restecg_0', 62 | 'restecg_1', 'restecg_2']) 63 | placeholder_df = pd.DataFrame() 64 | 65 | # One-Hot Encoding using get_dummies for the specified categorical features 66 | for f in features: 67 | if(f in df.columns): 68 | encoded = pd.get_dummies(df[f]) 69 | encoded = encoded.add_prefix(f + '_') 70 | placeholder_df = pd.concat([placeholder_df, encoded], axis=1) 71 | else: 72 | print('Feature not found') 73 | return df 74 | 75 | # Implement these steps to prevent dimension mismatch during inference 76 | for feature in encoded_df.columns: 77 | if feature in df.columns: 78 | encoded_df[feature] = df[feature] 79 | if feature in placeholder_df.columns: 80 | encoded_df[feature] = placeholder_df[feature] 81 | # fill all null values 82 | encoded_df.fillna(0, inplace=True) 83 | 84 | return encoded_df 85 | 86 | 87 | def normalize_data(df): 88 | ''' 89 | Normalize data using Min-Max Scaler 90 | Input: The method takes pandas dataframe as input 91 | Output: Returns a dataframe with normalized features 92 | Example usage: 93 | normalized_df = normalize_data(df) 94 | ''' 95 | val = df.values 96 | min_max_normalizer = preprocessing.MinMaxScaler() 97 | norm_val = min_max_normalizer.fit_transform(val) 98 | df2 = pd.DataFrame(norm_val) 99 | return df2 100 | 101 | 102 | def apply_pre_processing(data): 103 | ''' 104 | Normalize data using Min-Max Scaler 105 | Input: The method takes pandas dataframe as input 106 | Output: Returns a dataframe with normalized features 107 | Example usage: 108 | normalized_df = normalize_data(df) 109 | ''' 110 | features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg'] 111 | encoded = encode_features(data, features_to_encode) 112 | processed_data = normalize_data(encoded) 113 | # Please note this is fabricated inference data, 114 | # so just taking a small sample size 115 | return processed_data 116 | 117 | 118 | # main function - starting point of the code 119 | def main(model_name, logger): 120 | ''' 121 | main function - starting point of the code 122 | ''' 123 | try: 124 | print("Starting execution of the inference code...") 125 | logger.info("Started execution. Fetching data now ...") 126 | inference_data, labels = get_inference_data() 127 | logger.info("Data fetched. Applying pre-processing now ...") 128 | processed_inference_data = apply_pre_processing(inference_data) 129 | # ### Load Saved Model 130 | logger.info("Pre-processing is completed. Loading trained model now ...") 131 | model = joblib.load(model_name) 132 | logger.info("Trained model is loaded. Executing trained model on inference data ...") 133 | # ### Prediction on inference data 134 | model.predict(processed_inference_data) 135 | # ### Scoring check on prediction 136 | print("Checking inference accuracy:") 137 | print(accuracy_score(labels[-20:], model.predict(processed_inference_data))) 138 | logger.info("Execution is complete.") 139 | except Exception as e: 140 | print("--------Error!!!--------") 141 | logger.error("Encountered error. Please check.") 142 | logger.error(e) 143 | print(e) 144 | 145 | 146 | 147 | if __name__ == "__main__": 148 | # Create and configure logger 149 | logging.basicConfig(filename="inference_pipe_exec.log", 150 | format='%(asctime)s %(message)s', 151 | filemode='a') 152 | 153 | # Creating an object 154 | logger = logging.getLogger() 155 | 156 | # Setting the threshold of logger to DEBUG 157 | logger.setLevel(logging.DEBUG) 158 | 159 | parser = argparse.ArgumentParser(description='Running inference pipeline') 160 | parser.add_argument('--model', 161 | default='adaboost', 162 | help='select algorithm: svm or adaboost') 163 | args = parser.parse_args() 164 | if(args.model == 'svm'): 165 | model_name = 'aditya_model2_svm.joblib' 166 | else: 167 | model_name = 'aditya_model1_adaboost.joblib' 168 | main(model_name, logger) -------------------------------------------------------------------------------- /unit testing/Data/heart.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 63,1,3,145,233,1,0,150,0,2.3,0,0,1,1 3 | 37,1,2,130,250,0,1,187,0,3.5,0,0,2,1 4 | 41,0,1,130,204,0,0,172,0,1.4,2,0,2,1 5 | 56,1,1,120,236,0,1,178,0,0.8,2,0,2,1 6 | 57,0,0,120,354,0,1,163,1,0.6,2,0,2,1 7 | 57,1,0,140,192,0,1,148,0,0.4,1,0,1,1 8 | 56,0,1,140,294,0,0,153,0,1.3,1,0,2,1 9 | 44,1,1,120,263,0,1,173,0,0,2,0,3,1 10 | 52,1,2,172,199,1,1,162,0,0.5,2,0,3,1 11 | 57,1,2,150,168,0,1,174,0,1.6,2,0,2,1 12 | 54,1,0,140,239,0,1,160,0,1.2,2,0,2,1 13 | 48,0,2,130,275,0,1,139,0,0.2,2,0,2,1 14 | 49,1,1,130,266,0,1,171,0,0.6,2,0,2,1 15 | 64,1,3,110,211,0,0,144,1,1.8,1,0,2,1 16 | 58,0,3,150,283,1,0,162,0,1,2,0,2,1 17 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 18 | 58,0,2,120,340,0,1,172,0,0,2,0,2,1 19 | 66,0,3,150,226,0,1,114,0,2.6,0,0,2,1 20 | 43,1,0,150,247,0,1,171,0,1.5,2,0,2,1 21 | 69,0,3,140,239,0,1,151,0,1.8,2,2,2,1 22 | 59,1,0,135,234,0,1,161,0,0.5,1,0,3,1 23 | 44,1,2,130,233,0,1,179,1,0.4,2,0,2,1 24 | 42,1,0,140,226,0,1,178,0,0,2,0,2,1 25 | 61,1,2,150,243,1,1,137,1,1,1,0,2,1 26 | 40,1,3,140,199,0,1,178,1,1.4,2,0,3,1 27 | 71,0,1,160,302,0,1,162,0,0.4,2,2,2,1 28 | 59,1,2,150,212,1,1,157,0,1.6,2,0,2,1 29 | 51,1,2,110,175,0,1,123,0,0.6,2,0,2,1 30 | 65,0,2,140,417,1,0,157,0,0.8,2,1,2,1 31 | 53,1,2,130,197,1,0,152,0,1.2,0,0,2,1 32 | 41,0,1,105,198,0,1,168,0,0,2,1,2,1 33 | 65,1,0,120,177,0,1,140,0,0.4,2,0,3,1 34 | 44,1,1,130,219,0,0,188,0,0,2,0,2,1 35 | 54,1,2,125,273,0,0,152,0,0.5,0,1,2,1 36 | 51,1,3,125,213,0,0,125,1,1.4,2,1,2,1 37 | 46,0,2,142,177,0,0,160,1,1.4,0,0,2,1 38 | 54,0,2,135,304,1,1,170,0,0,2,0,2,1 39 | 54,1,2,150,232,0,0,165,0,1.6,2,0,3,1 40 | 65,0,2,155,269,0,1,148,0,0.8,2,0,2,1 41 | 65,0,2,160,360,0,0,151,0,0.8,2,0,2,1 42 | 51,0,2,140,308,0,0,142,0,1.5,2,1,2,1 43 | 48,1,1,130,245,0,0,180,0,0.2,1,0,2,1 44 | 45,1,0,104,208,0,0,148,1,3,1,0,2,1 45 | 53,0,0,130,264,0,0,143,0,0.4,1,0,2,1 46 | 39,1,2,140,321,0,0,182,0,0,2,0,2,1 47 | 52,1,1,120,325,0,1,172,0,0.2,2,0,2,1 48 | 44,1,2,140,235,0,0,180,0,0,2,0,2,1 49 | 47,1,2,138,257,0,0,156,0,0,2,0,2,1 50 | 53,0,2,128,216,0,0,115,0,0,2,0,0,1 51 | 53,0,0,138,234,0,0,160,0,0,2,0,2,1 52 | 51,0,2,130,256,0,0,149,0,0.5,2,0,2,1 53 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 54 | 62,1,2,130,231,0,1,146,0,1.8,1,3,3,1 55 | 44,0,2,108,141,0,1,175,0,0.6,1,0,2,1 56 | 63,0,2,135,252,0,0,172,0,0,2,0,2,1 57 | 52,1,1,134,201,0,1,158,0,0.8,2,1,2,1 58 | 48,1,0,122,222,0,0,186,0,0,2,0,2,1 59 | 45,1,0,115,260,0,0,185,0,0,2,0,2,1 60 | 34,1,3,118,182,0,0,174,0,0,2,0,2,1 61 | 57,0,0,128,303,0,0,159,0,0,2,1,2,1 62 | 71,0,2,110,265,1,0,130,0,0,2,1,2,1 63 | 54,1,1,108,309,0,1,156,0,0,2,0,3,1 64 | 52,1,3,118,186,0,0,190,0,0,1,0,1,1 65 | 41,1,1,135,203,0,1,132,0,0,1,0,1,1 66 | 58,1,2,140,211,1,0,165,0,0,2,0,2,1 67 | 35,0,0,138,183,0,1,182,0,1.4,2,0,2,1 68 | 51,1,2,100,222,0,1,143,1,1.2,1,0,2,1 69 | 45,0,1,130,234,0,0,175,0,0.6,1,0,2,1 70 | 44,1,1,120,220,0,1,170,0,0,2,0,2,1 71 | 62,0,0,124,209,0,1,163,0,0,2,0,2,1 72 | 54,1,2,120,258,0,0,147,0,0.4,1,0,3,1 73 | 51,1,2,94,227,0,1,154,1,0,2,1,3,1 74 | 29,1,1,130,204,0,0,202,0,0,2,0,2,1 75 | 51,1,0,140,261,0,0,186,1,0,2,0,2,1 76 | 43,0,2,122,213,0,1,165,0,0.2,1,0,2,1 77 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 78 | 51,1,2,125,245,1,0,166,0,2.4,1,0,2,1 79 | 59,1,1,140,221,0,1,164,1,0,2,0,2,1 80 | 52,1,1,128,205,1,1,184,0,0,2,0,2,1 81 | 58,1,2,105,240,0,0,154,1,0.6,1,0,3,1 82 | 41,1,2,112,250,0,1,179,0,0,2,0,2,1 83 | 45,1,1,128,308,0,0,170,0,0,2,0,2,1 84 | 60,0,2,102,318,0,1,160,0,0,2,1,2,1 85 | 52,1,3,152,298,1,1,178,0,1.2,1,0,3,1 86 | 42,0,0,102,265,0,0,122,0,0.6,1,0,2,1 87 | 67,0,2,115,564,0,0,160,0,1.6,1,0,3,1 88 | 68,1,2,118,277,0,1,151,0,1,2,1,3,1 89 | 46,1,1,101,197,1,1,156,0,0,2,0,3,1 90 | 54,0,2,110,214,0,1,158,0,1.6,1,0,2,1 91 | 58,0,0,100,248,0,0,122,0,1,1,0,2,1 92 | 48,1,2,124,255,1,1,175,0,0,2,2,2,1 93 | 57,1,0,132,207,0,1,168,1,0,2,0,3,1 94 | 52,1,2,138,223,0,1,169,0,0,2,4,2,1 95 | 54,0,1,132,288,1,0,159,1,0,2,1,2,1 96 | 45,0,1,112,160,0,1,138,0,0,1,0,2,1 97 | 53,1,0,142,226,0,0,111,1,0,2,0,3,1 98 | 62,0,0,140,394,0,0,157,0,1.2,1,0,2,1 99 | 52,1,0,108,233,1,1,147,0,0.1,2,3,3,1 100 | 43,1,2,130,315,0,1,162,0,1.9,2,1,2,1 101 | 53,1,2,130,246,1,0,173,0,0,2,3,2,1 102 | 42,1,3,148,244,0,0,178,0,0.8,2,2,2,1 103 | 59,1,3,178,270,0,0,145,0,4.2,0,0,3,1 104 | 63,0,1,140,195,0,1,179,0,0,2,2,2,1 105 | 42,1,2,120,240,1,1,194,0,0.8,0,0,3,1 106 | 50,1,2,129,196,0,1,163,0,0,2,0,2,1 107 | 68,0,2,120,211,0,0,115,0,1.5,1,0,2,1 108 | 69,1,3,160,234,1,0,131,0,0.1,1,1,2,1 109 | 45,0,0,138,236,0,0,152,1,0.2,1,0,2,1 110 | 50,0,1,120,244,0,1,162,0,1.1,2,0,2,1 111 | 50,0,0,110,254,0,0,159,0,0,2,0,2,1 112 | 64,0,0,180,325,0,1,154,1,0,2,0,2,1 113 | 57,1,2,150,126,1,1,173,0,0.2,2,1,3,1 114 | 64,0,2,140,313,0,1,133,0,0.2,2,0,3,1 115 | 43,1,0,110,211,0,1,161,0,0,2,0,3,1 116 | 55,1,1,130,262,0,1,155,0,0,2,0,2,1 117 | 37,0,2,120,215,0,1,170,0,0,2,0,2,1 118 | 41,1,2,130,214,0,0,168,0,2,1,0,2,1 119 | 56,1,3,120,193,0,0,162,0,1.9,1,0,3,1 120 | 46,0,1,105,204,0,1,172,0,0,2,0,2,1 121 | 46,0,0,138,243,0,0,152,1,0,1,0,2,1 122 | 64,0,0,130,303,0,1,122,0,2,1,2,2,1 123 | 59,1,0,138,271,0,0,182,0,0,2,0,2,1 124 | 41,0,2,112,268,0,0,172,1,0,2,0,2,1 125 | 54,0,2,108,267,0,0,167,0,0,2,0,2,1 126 | 39,0,2,94,199,0,1,179,0,0,2,0,2,1 127 | 34,0,1,118,210,0,1,192,0,0.7,2,0,2,1 128 | 47,1,0,112,204,0,1,143,0,0.1,2,0,2,1 129 | 67,0,2,152,277,0,1,172,0,0,2,1,2,1 130 | 52,0,2,136,196,0,0,169,0,0.1,1,0,2,1 131 | 74,0,1,120,269,0,0,121,1,0.2,2,1,2,1 132 | 54,0,2,160,201,0,1,163,0,0,2,1,2,1 133 | 49,0,1,134,271,0,1,162,0,0,1,0,2,1 134 | 42,1,1,120,295,0,1,162,0,0,2,0,2,1 135 | 41,1,1,110,235,0,1,153,0,0,2,0,2,1 136 | 41,0,1,126,306,0,1,163,0,0,2,0,2,1 137 | 49,0,0,130,269,0,1,163,0,0,2,0,2,1 138 | 60,0,2,120,178,1,1,96,0,0,2,0,2,1 139 | 62,1,1,128,208,1,0,140,0,0,2,0,2,1 140 | 57,1,0,110,201,0,1,126,1,1.5,1,0,1,1 141 | 64,1,0,128,263,0,1,105,1,0.2,1,1,3,1 142 | 51,0,2,120,295,0,0,157,0,0.6,2,0,2,1 143 | 43,1,0,115,303,0,1,181,0,1.2,1,0,2,1 144 | 42,0,2,120,209,0,1,173,0,0,1,0,2,1 145 | 67,0,0,106,223,0,1,142,0,0.3,2,2,2,1 146 | 76,0,2,140,197,0,2,116,0,1.1,1,0,2,1 147 | 70,1,1,156,245,0,0,143,0,0,2,0,2,1 148 | 44,0,2,118,242,0,1,149,0,0.3,1,1,2,1 149 | 60,0,3,150,240,0,1,171,0,0.9,2,0,2,1 150 | 44,1,2,120,226,0,1,169,0,0,2,0,2,1 151 | 42,1,2,130,180,0,1,150,0,0,2,0,2,1 152 | 66,1,0,160,228,0,0,138,0,2.3,2,0,1,1 153 | 71,0,0,112,149,0,1,125,0,1.6,1,0,2,1 154 | 64,1,3,170,227,0,0,155,0,0.6,1,0,3,1 155 | 66,0,2,146,278,0,0,152,0,0,1,1,2,1 156 | 39,0,2,138,220,0,1,152,0,0,1,0,2,1 157 | 58,0,0,130,197,0,1,131,0,0.6,1,0,2,1 158 | 47,1,2,130,253,0,1,179,0,0,2,0,2,1 159 | 35,1,1,122,192,0,1,174,0,0,2,0,2,1 160 | 58,1,1,125,220,0,1,144,0,0.4,1,4,3,1 161 | 56,1,1,130,221,0,0,163,0,0,2,0,3,1 162 | 56,1,1,120,240,0,1,169,0,0,0,0,2,1 163 | 55,0,1,132,342,0,1,166,0,1.2,2,0,2,1 164 | 41,1,1,120,157,0,1,182,0,0,2,0,2,1 165 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 166 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 167 | 67,1,0,160,286,0,0,108,1,1.5,1,3,2,0 168 | 67,1,0,120,229,0,0,129,1,2.6,1,2,3,0 169 | 62,0,0,140,268,0,0,160,0,3.6,0,2,2,0 170 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 171 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 172 | 56,1,2,130,256,1,0,142,1,0.6,1,1,1,0 173 | 48,1,1,110,229,0,1,168,0,1,0,0,3,0 174 | 58,1,1,120,284,0,0,160,0,1.8,1,0,2,0 175 | 58,1,2,132,224,0,0,173,0,3.2,2,2,3,0 176 | 60,1,0,130,206,0,0,132,1,2.4,1,2,3,0 177 | 40,1,0,110,167,0,0,114,1,2,1,0,3,0 178 | 60,1,0,117,230,1,1,160,1,1.4,2,2,3,0 179 | 64,1,2,140,335,0,1,158,0,0,2,0,2,0 180 | 43,1,0,120,177,0,0,120,1,2.5,1,0,3,0 181 | 57,1,0,150,276,0,0,112,1,0.6,1,1,1,0 182 | 55,1,0,132,353,0,1,132,1,1.2,1,1,3,0 183 | 65,0,0,150,225,0,0,114,0,1,1,3,3,0 184 | 61,0,0,130,330,0,0,169,0,0,2,0,2,0 185 | 58,1,2,112,230,0,0,165,0,2.5,1,1,3,0 186 | 50,1,0,150,243,0,0,128,0,2.6,1,0,3,0 187 | 44,1,0,112,290,0,0,153,0,0,2,1,2,0 188 | 60,1,0,130,253,0,1,144,1,1.4,2,1,3,0 189 | 54,1,0,124,266,0,0,109,1,2.2,1,1,3,0 190 | 50,1,2,140,233,0,1,163,0,0.6,1,1,3,0 191 | 41,1,0,110,172,0,0,158,0,0,2,0,3,0 192 | 51,0,0,130,305,0,1,142,1,1.2,1,0,3,0 193 | 58,1,0,128,216,0,0,131,1,2.2,1,3,3,0 194 | 54,1,0,120,188,0,1,113,0,1.4,1,1,3,0 195 | 60,1,0,145,282,0,0,142,1,2.8,1,2,3,0 196 | 60,1,2,140,185,0,0,155,0,3,1,0,2,0 197 | 59,1,0,170,326,0,0,140,1,3.4,0,0,3,0 198 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 199 | 67,1,0,125,254,1,1,163,0,0.2,1,2,3,0 200 | 62,1,0,120,267,0,1,99,1,1.8,1,2,3,0 201 | 65,1,0,110,248,0,0,158,0,0.6,2,2,1,0 202 | 44,1,0,110,197,0,0,177,0,0,2,1,2,0 203 | 60,1,0,125,258,0,0,141,1,2.8,1,1,3,0 204 | 58,1,0,150,270,0,0,111,1,0.8,2,0,3,0 205 | 68,1,2,180,274,1,0,150,1,1.6,1,0,3,0 206 | 62,0,0,160,164,0,0,145,0,6.2,0,3,3,0 207 | 52,1,0,128,255,0,1,161,1,0,2,1,3,0 208 | 59,1,0,110,239,0,0,142,1,1.2,1,1,3,0 209 | 60,0,0,150,258,0,0,157,0,2.6,1,2,3,0 210 | 49,1,2,120,188,0,1,139,0,2,1,3,3,0 211 | 59,1,0,140,177,0,1,162,1,0,2,1,3,0 212 | 57,1,2,128,229,0,0,150,0,0.4,1,1,3,0 213 | 61,1,0,120,260,0,1,140,1,3.6,1,1,3,0 214 | 39,1,0,118,219,0,1,140,0,1.2,1,0,3,0 215 | 61,0,0,145,307,0,0,146,1,1,1,0,3,0 216 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 217 | 43,0,0,132,341,1,0,136,1,3,1,0,3,0 218 | 62,0,2,130,263,0,1,97,0,1.2,1,1,3,0 219 | 63,1,0,130,330,1,0,132,1,1.8,2,3,3,0 220 | 65,1,0,135,254,0,0,127,0,2.8,1,1,3,0 221 | 48,1,0,130,256,1,0,150,1,0,2,2,3,0 222 | 63,0,0,150,407,0,0,154,0,4,1,3,3,0 223 | 55,1,0,140,217,0,1,111,1,5.6,0,0,3,0 224 | 65,1,3,138,282,1,0,174,0,1.4,1,1,2,0 225 | 56,0,0,200,288,1,0,133,1,4,0,2,3,0 226 | 54,1,0,110,239,0,1,126,1,2.8,1,1,3,0 227 | 70,1,0,145,174,0,1,125,1,2.6,0,0,3,0 228 | 62,1,1,120,281,0,0,103,0,1.4,1,1,3,0 229 | 35,1,0,120,198,0,1,130,1,1.6,1,0,3,0 230 | 59,1,3,170,288,0,0,159,0,0.2,1,0,3,0 231 | 64,1,2,125,309,0,1,131,1,1.8,1,0,3,0 232 | 47,1,2,108,243,0,1,152,0,0,2,0,2,0 233 | 57,1,0,165,289,1,0,124,0,1,1,3,3,0 234 | 55,1,0,160,289,0,0,145,1,0.8,1,1,3,0 235 | 64,1,0,120,246,0,0,96,1,2.2,0,1,2,0 236 | 70,1,0,130,322,0,0,109,0,2.4,1,3,2,0 237 | 51,1,0,140,299,0,1,173,1,1.6,2,0,3,0 238 | 58,1,0,125,300,0,0,171,0,0,2,2,3,0 239 | 60,1,0,140,293,0,0,170,0,1.2,1,2,3,0 240 | 77,1,0,125,304,0,0,162,1,0,2,3,2,0 241 | 35,1,0,126,282,0,0,156,1,0,2,0,3,0 242 | 70,1,2,160,269,0,1,112,1,2.9,1,1,3,0 243 | 59,0,0,174,249,0,1,143,1,0,1,0,2,0 244 | 64,1,0,145,212,0,0,132,0,2,1,2,1,0 245 | 57,1,0,152,274,0,1,88,1,1.2,1,1,3,0 246 | 56,1,0,132,184,0,0,105,1,2.1,1,1,1,0 247 | 48,1,0,124,274,0,0,166,0,0.5,1,0,3,0 248 | 56,0,0,134,409,0,0,150,1,1.9,1,2,3,0 249 | 66,1,1,160,246,0,1,120,1,0,1,3,1,0 250 | 54,1,1,192,283,0,0,195,0,0,2,1,3,0 251 | 69,1,2,140,254,0,0,146,0,2,1,3,3,0 252 | 51,1,0,140,298,0,1,122,1,4.2,1,3,3,0 253 | 43,1,0,132,247,1,0,143,1,0.1,1,4,3,0 254 | 62,0,0,138,294,1,1,106,0,1.9,1,3,2,0 255 | 67,1,0,100,299,0,0,125,1,0.9,1,2,2,0 256 | 59,1,3,160,273,0,0,125,0,0,2,0,2,0 257 | 45,1,0,142,309,0,0,147,1,0,1,3,3,0 258 | 58,1,0,128,259,0,0,130,1,3,1,2,3,0 259 | 50,1,0,144,200,0,0,126,1,0.9,1,0,3,0 260 | 62,0,0,150,244,0,1,154,1,1.4,1,0,2,0 261 | 38,1,3,120,231,0,1,182,1,3.8,1,0,3,0 262 | 66,0,0,178,228,1,1,165,1,1,1,2,3,0 263 | 52,1,0,112,230,0,1,160,0,0,2,1,2,0 264 | 53,1,0,123,282,0,1,95,1,2,1,2,3,0 265 | 63,0,0,108,269,0,1,169,1,1.8,1,2,2,0 266 | 54,1,0,110,206,0,0,108,1,0,1,1,2,0 267 | 66,1,0,112,212,0,0,132,1,0.1,2,1,2,0 268 | 55,0,0,180,327,0,2,117,1,3.4,1,0,2,0 269 | 49,1,2,118,149,0,0,126,0,0.8,2,3,2,0 270 | 54,1,0,122,286,0,0,116,1,3.2,1,2,2,0 271 | 56,1,0,130,283,1,0,103,1,1.6,0,0,3,0 272 | 46,1,0,120,249,0,0,144,0,0.8,2,0,3,0 273 | 61,1,3,134,234,0,1,145,0,2.6,1,2,2,0 274 | 67,1,0,120,237,0,1,71,0,1,1,0,2,0 275 | 58,1,0,100,234,0,1,156,0,0.1,2,1,3,0 276 | 47,1,0,110,275,0,0,118,1,1,1,1,2,0 277 | 52,1,0,125,212,0,1,168,0,1,2,2,3,0 278 | 58,1,0,146,218,0,1,105,0,2,1,1,3,0 279 | 57,1,1,124,261,0,1,141,0,0.3,2,0,3,0 280 | 58,0,1,136,319,1,0,152,0,0,2,2,2,0 281 | 61,1,0,138,166,0,0,125,1,3.6,1,1,2,0 282 | 42,1,0,136,315,0,1,125,1,1.8,1,0,1,0 283 | 52,1,0,128,204,1,1,156,1,1,1,0,0,0 284 | 59,1,2,126,218,1,1,134,0,2.2,1,1,1,0 285 | 40,1,0,152,223,0,1,181,0,0,2,0,3,0 286 | 61,1,0,140,207,0,0,138,1,1.9,2,1,3,0 287 | 46,1,0,140,311,0,1,120,1,1.8,1,2,3,0 288 | 59,1,3,134,204,0,1,162,0,0.8,2,2,2,0 289 | 57,1,1,154,232,0,0,164,0,0,2,1,2,0 290 | 57,1,0,110,335,0,1,143,1,3,1,1,3,0 291 | 55,0,0,128,205,0,2,130,1,2,1,1,3,0 292 | 61,1,0,148,203,0,1,161,0,0,2,1,3,0 293 | 58,1,0,114,318,0,2,140,0,4.4,0,3,1,0 294 | 58,0,0,170,225,1,0,146,1,2.8,1,2,1,0 295 | 67,1,2,152,212,0,0,150,0,0.8,1,0,3,0 296 | 44,1,0,120,169,0,1,144,1,2.8,0,0,1,0 297 | 63,1,0,140,187,0,0,144,1,4,2,2,3,0 298 | 63,0,0,124,197,0,1,136,1,0,1,0,2,0 299 | 59,1,0,164,176,1,0,90,0,1,1,2,1,0 300 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 301 | 45,1,3,110,264,0,1,132,0,1.2,1,0,3,0 302 | 68,1,0,144,193,1,1,141,0,3.4,1,2,3,0 303 | 57,1,0,130,131,0,1,115,1,1.2,1,1,3,0 304 | 57,0,1,130,236,0,0,174,0,0,1,1,2,0 305 | -------------------------------------------------------------------------------- /python scripting/Data/heart.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 63,1,3,145,233,1,0,150,0,2.3,0,0,1,1 3 | 37,1,2,130,250,0,1,187,0,3.5,0,0,2,1 4 | 41,0,1,130,204,0,0,172,0,1.4,2,0,2,1 5 | 56,1,1,120,236,0,1,178,0,0.8,2,0,2,1 6 | 57,0,0,120,354,0,1,163,1,0.6,2,0,2,1 7 | 57,1,0,140,192,0,1,148,0,0.4,1,0,1,1 8 | 56,0,1,140,294,0,0,153,0,1.3,1,0,2,1 9 | 44,1,1,120,263,0,1,173,0,0,2,0,3,1 10 | 52,1,2,172,199,1,1,162,0,0.5,2,0,3,1 11 | 57,1,2,150,168,0,1,174,0,1.6,2,0,2,1 12 | 54,1,0,140,239,0,1,160,0,1.2,2,0,2,1 13 | 48,0,2,130,275,0,1,139,0,0.2,2,0,2,1 14 | 49,1,1,130,266,0,1,171,0,0.6,2,0,2,1 15 | 64,1,3,110,211,0,0,144,1,1.8,1,0,2,1 16 | 58,0,3,150,283,1,0,162,0,1,2,0,2,1 17 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 18 | 58,0,2,120,340,0,1,172,0,0,2,0,2,1 19 | 66,0,3,150,226,0,1,114,0,2.6,0,0,2,1 20 | 43,1,0,150,247,0,1,171,0,1.5,2,0,2,1 21 | 69,0,3,140,239,0,1,151,0,1.8,2,2,2,1 22 | 59,1,0,135,234,0,1,161,0,0.5,1,0,3,1 23 | 44,1,2,130,233,0,1,179,1,0.4,2,0,2,1 24 | 42,1,0,140,226,0,1,178,0,0,2,0,2,1 25 | 61,1,2,150,243,1,1,137,1,1,1,0,2,1 26 | 40,1,3,140,199,0,1,178,1,1.4,2,0,3,1 27 | 71,0,1,160,302,0,1,162,0,0.4,2,2,2,1 28 | 59,1,2,150,212,1,1,157,0,1.6,2,0,2,1 29 | 51,1,2,110,175,0,1,123,0,0.6,2,0,2,1 30 | 65,0,2,140,417,1,0,157,0,0.8,2,1,2,1 31 | 53,1,2,130,197,1,0,152,0,1.2,0,0,2,1 32 | 41,0,1,105,198,0,1,168,0,0,2,1,2,1 33 | 65,1,0,120,177,0,1,140,0,0.4,2,0,3,1 34 | 44,1,1,130,219,0,0,188,0,0,2,0,2,1 35 | 54,1,2,125,273,0,0,152,0,0.5,0,1,2,1 36 | 51,1,3,125,213,0,0,125,1,1.4,2,1,2,1 37 | 46,0,2,142,177,0,0,160,1,1.4,0,0,2,1 38 | 54,0,2,135,304,1,1,170,0,0,2,0,2,1 39 | 54,1,2,150,232,0,0,165,0,1.6,2,0,3,1 40 | 65,0,2,155,269,0,1,148,0,0.8,2,0,2,1 41 | 65,0,2,160,360,0,0,151,0,0.8,2,0,2,1 42 | 51,0,2,140,308,0,0,142,0,1.5,2,1,2,1 43 | 48,1,1,130,245,0,0,180,0,0.2,1,0,2,1 44 | 45,1,0,104,208,0,0,148,1,3,1,0,2,1 45 | 53,0,0,130,264,0,0,143,0,0.4,1,0,2,1 46 | 39,1,2,140,321,0,0,182,0,0,2,0,2,1 47 | 52,1,1,120,325,0,1,172,0,0.2,2,0,2,1 48 | 44,1,2,140,235,0,0,180,0,0,2,0,2,1 49 | 47,1,2,138,257,0,0,156,0,0,2,0,2,1 50 | 53,0,2,128,216,0,0,115,0,0,2,0,0,1 51 | 53,0,0,138,234,0,0,160,0,0,2,0,2,1 52 | 51,0,2,130,256,0,0,149,0,0.5,2,0,2,1 53 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 54 | 62,1,2,130,231,0,1,146,0,1.8,1,3,3,1 55 | 44,0,2,108,141,0,1,175,0,0.6,1,0,2,1 56 | 63,0,2,135,252,0,0,172,0,0,2,0,2,1 57 | 52,1,1,134,201,0,1,158,0,0.8,2,1,2,1 58 | 48,1,0,122,222,0,0,186,0,0,2,0,2,1 59 | 45,1,0,115,260,0,0,185,0,0,2,0,2,1 60 | 34,1,3,118,182,0,0,174,0,0,2,0,2,1 61 | 57,0,0,128,303,0,0,159,0,0,2,1,2,1 62 | 71,0,2,110,265,1,0,130,0,0,2,1,2,1 63 | 54,1,1,108,309,0,1,156,0,0,2,0,3,1 64 | 52,1,3,118,186,0,0,190,0,0,1,0,1,1 65 | 41,1,1,135,203,0,1,132,0,0,1,0,1,1 66 | 58,1,2,140,211,1,0,165,0,0,2,0,2,1 67 | 35,0,0,138,183,0,1,182,0,1.4,2,0,2,1 68 | 51,1,2,100,222,0,1,143,1,1.2,1,0,2,1 69 | 45,0,1,130,234,0,0,175,0,0.6,1,0,2,1 70 | 44,1,1,120,220,0,1,170,0,0,2,0,2,1 71 | 62,0,0,124,209,0,1,163,0,0,2,0,2,1 72 | 54,1,2,120,258,0,0,147,0,0.4,1,0,3,1 73 | 51,1,2,94,227,0,1,154,1,0,2,1,3,1 74 | 29,1,1,130,204,0,0,202,0,0,2,0,2,1 75 | 51,1,0,140,261,0,0,186,1,0,2,0,2,1 76 | 43,0,2,122,213,0,1,165,0,0.2,1,0,2,1 77 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 78 | 51,1,2,125,245,1,0,166,0,2.4,1,0,2,1 79 | 59,1,1,140,221,0,1,164,1,0,2,0,2,1 80 | 52,1,1,128,205,1,1,184,0,0,2,0,2,1 81 | 58,1,2,105,240,0,0,154,1,0.6,1,0,3,1 82 | 41,1,2,112,250,0,1,179,0,0,2,0,2,1 83 | 45,1,1,128,308,0,0,170,0,0,2,0,2,1 84 | 60,0,2,102,318,0,1,160,0,0,2,1,2,1 85 | 52,1,3,152,298,1,1,178,0,1.2,1,0,3,1 86 | 42,0,0,102,265,0,0,122,0,0.6,1,0,2,1 87 | 67,0,2,115,564,0,0,160,0,1.6,1,0,3,1 88 | 68,1,2,118,277,0,1,151,0,1,2,1,3,1 89 | 46,1,1,101,197,1,1,156,0,0,2,0,3,1 90 | 54,0,2,110,214,0,1,158,0,1.6,1,0,2,1 91 | 58,0,0,100,248,0,0,122,0,1,1,0,2,1 92 | 48,1,2,124,255,1,1,175,0,0,2,2,2,1 93 | 57,1,0,132,207,0,1,168,1,0,2,0,3,1 94 | 52,1,2,138,223,0,1,169,0,0,2,4,2,1 95 | 54,0,1,132,288,1,0,159,1,0,2,1,2,1 96 | 45,0,1,112,160,0,1,138,0,0,1,0,2,1 97 | 53,1,0,142,226,0,0,111,1,0,2,0,3,1 98 | 62,0,0,140,394,0,0,157,0,1.2,1,0,2,1 99 | 52,1,0,108,233,1,1,147,0,0.1,2,3,3,1 100 | 43,1,2,130,315,0,1,162,0,1.9,2,1,2,1 101 | 53,1,2,130,246,1,0,173,0,0,2,3,2,1 102 | 42,1,3,148,244,0,0,178,0,0.8,2,2,2,1 103 | 59,1,3,178,270,0,0,145,0,4.2,0,0,3,1 104 | 63,0,1,140,195,0,1,179,0,0,2,2,2,1 105 | 42,1,2,120,240,1,1,194,0,0.8,0,0,3,1 106 | 50,1,2,129,196,0,1,163,0,0,2,0,2,1 107 | 68,0,2,120,211,0,0,115,0,1.5,1,0,2,1 108 | 69,1,3,160,234,1,0,131,0,0.1,1,1,2,1 109 | 45,0,0,138,236,0,0,152,1,0.2,1,0,2,1 110 | 50,0,1,120,244,0,1,162,0,1.1,2,0,2,1 111 | 50,0,0,110,254,0,0,159,0,0,2,0,2,1 112 | 64,0,0,180,325,0,1,154,1,0,2,0,2,1 113 | 57,1,2,150,126,1,1,173,0,0.2,2,1,3,1 114 | 64,0,2,140,313,0,1,133,0,0.2,2,0,3,1 115 | 43,1,0,110,211,0,1,161,0,0,2,0,3,1 116 | 55,1,1,130,262,0,1,155,0,0,2,0,2,1 117 | 37,0,2,120,215,0,1,170,0,0,2,0,2,1 118 | 41,1,2,130,214,0,0,168,0,2,1,0,2,1 119 | 56,1,3,120,193,0,0,162,0,1.9,1,0,3,1 120 | 46,0,1,105,204,0,1,172,0,0,2,0,2,1 121 | 46,0,0,138,243,0,0,152,1,0,1,0,2,1 122 | 64,0,0,130,303,0,1,122,0,2,1,2,2,1 123 | 59,1,0,138,271,0,0,182,0,0,2,0,2,1 124 | 41,0,2,112,268,0,0,172,1,0,2,0,2,1 125 | 54,0,2,108,267,0,0,167,0,0,2,0,2,1 126 | 39,0,2,94,199,0,1,179,0,0,2,0,2,1 127 | 34,0,1,118,210,0,1,192,0,0.7,2,0,2,1 128 | 47,1,0,112,204,0,1,143,0,0.1,2,0,2,1 129 | 67,0,2,152,277,0,1,172,0,0,2,1,2,1 130 | 52,0,2,136,196,0,0,169,0,0.1,1,0,2,1 131 | 74,0,1,120,269,0,0,121,1,0.2,2,1,2,1 132 | 54,0,2,160,201,0,1,163,0,0,2,1,2,1 133 | 49,0,1,134,271,0,1,162,0,0,1,0,2,1 134 | 42,1,1,120,295,0,1,162,0,0,2,0,2,1 135 | 41,1,1,110,235,0,1,153,0,0,2,0,2,1 136 | 41,0,1,126,306,0,1,163,0,0,2,0,2,1 137 | 49,0,0,130,269,0,1,163,0,0,2,0,2,1 138 | 60,0,2,120,178,1,1,96,0,0,2,0,2,1 139 | 62,1,1,128,208,1,0,140,0,0,2,0,2,1 140 | 57,1,0,110,201,0,1,126,1,1.5,1,0,1,1 141 | 64,1,0,128,263,0,1,105,1,0.2,1,1,3,1 142 | 51,0,2,120,295,0,0,157,0,0.6,2,0,2,1 143 | 43,1,0,115,303,0,1,181,0,1.2,1,0,2,1 144 | 42,0,2,120,209,0,1,173,0,0,1,0,2,1 145 | 67,0,0,106,223,0,1,142,0,0.3,2,2,2,1 146 | 76,0,2,140,197,0,2,116,0,1.1,1,0,2,1 147 | 70,1,1,156,245,0,0,143,0,0,2,0,2,1 148 | 44,0,2,118,242,0,1,149,0,0.3,1,1,2,1 149 | 60,0,3,150,240,0,1,171,0,0.9,2,0,2,1 150 | 44,1,2,120,226,0,1,169,0,0,2,0,2,1 151 | 42,1,2,130,180,0,1,150,0,0,2,0,2,1 152 | 66,1,0,160,228,0,0,138,0,2.3,2,0,1,1 153 | 71,0,0,112,149,0,1,125,0,1.6,1,0,2,1 154 | 64,1,3,170,227,0,0,155,0,0.6,1,0,3,1 155 | 66,0,2,146,278,0,0,152,0,0,1,1,2,1 156 | 39,0,2,138,220,0,1,152,0,0,1,0,2,1 157 | 58,0,0,130,197,0,1,131,0,0.6,1,0,2,1 158 | 47,1,2,130,253,0,1,179,0,0,2,0,2,1 159 | 35,1,1,122,192,0,1,174,0,0,2,0,2,1 160 | 58,1,1,125,220,0,1,144,0,0.4,1,4,3,1 161 | 56,1,1,130,221,0,0,163,0,0,2,0,3,1 162 | 56,1,1,120,240,0,1,169,0,0,0,0,2,1 163 | 55,0,1,132,342,0,1,166,0,1.2,2,0,2,1 164 | 41,1,1,120,157,0,1,182,0,0,2,0,2,1 165 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 166 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 167 | 67,1,0,160,286,0,0,108,1,1.5,1,3,2,0 168 | 67,1,0,120,229,0,0,129,1,2.6,1,2,3,0 169 | 62,0,0,140,268,0,0,160,0,3.6,0,2,2,0 170 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 171 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 172 | 56,1,2,130,256,1,0,142,1,0.6,1,1,1,0 173 | 48,1,1,110,229,0,1,168,0,1,0,0,3,0 174 | 58,1,1,120,284,0,0,160,0,1.8,1,0,2,0 175 | 58,1,2,132,224,0,0,173,0,3.2,2,2,3,0 176 | 60,1,0,130,206,0,0,132,1,2.4,1,2,3,0 177 | 40,1,0,110,167,0,0,114,1,2,1,0,3,0 178 | 60,1,0,117,230,1,1,160,1,1.4,2,2,3,0 179 | 64,1,2,140,335,0,1,158,0,0,2,0,2,0 180 | 43,1,0,120,177,0,0,120,1,2.5,1,0,3,0 181 | 57,1,0,150,276,0,0,112,1,0.6,1,1,1,0 182 | 55,1,0,132,353,0,1,132,1,1.2,1,1,3,0 183 | 65,0,0,150,225,0,0,114,0,1,1,3,3,0 184 | 61,0,0,130,330,0,0,169,0,0,2,0,2,0 185 | 58,1,2,112,230,0,0,165,0,2.5,1,1,3,0 186 | 50,1,0,150,243,0,0,128,0,2.6,1,0,3,0 187 | 44,1,0,112,290,0,0,153,0,0,2,1,2,0 188 | 60,1,0,130,253,0,1,144,1,1.4,2,1,3,0 189 | 54,1,0,124,266,0,0,109,1,2.2,1,1,3,0 190 | 50,1,2,140,233,0,1,163,0,0.6,1,1,3,0 191 | 41,1,0,110,172,0,0,158,0,0,2,0,3,0 192 | 51,0,0,130,305,0,1,142,1,1.2,1,0,3,0 193 | 58,1,0,128,216,0,0,131,1,2.2,1,3,3,0 194 | 54,1,0,120,188,0,1,113,0,1.4,1,1,3,0 195 | 60,1,0,145,282,0,0,142,1,2.8,1,2,3,0 196 | 60,1,2,140,185,0,0,155,0,3,1,0,2,0 197 | 59,1,0,170,326,0,0,140,1,3.4,0,0,3,0 198 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 199 | 67,1,0,125,254,1,1,163,0,0.2,1,2,3,0 200 | 62,1,0,120,267,0,1,99,1,1.8,1,2,3,0 201 | 65,1,0,110,248,0,0,158,0,0.6,2,2,1,0 202 | 44,1,0,110,197,0,0,177,0,0,2,1,2,0 203 | 60,1,0,125,258,0,0,141,1,2.8,1,1,3,0 204 | 58,1,0,150,270,0,0,111,1,0.8,2,0,3,0 205 | 68,1,2,180,274,1,0,150,1,1.6,1,0,3,0 206 | 62,0,0,160,164,0,0,145,0,6.2,0,3,3,0 207 | 52,1,0,128,255,0,1,161,1,0,2,1,3,0 208 | 59,1,0,110,239,0,0,142,1,1.2,1,1,3,0 209 | 60,0,0,150,258,0,0,157,0,2.6,1,2,3,0 210 | 49,1,2,120,188,0,1,139,0,2,1,3,3,0 211 | 59,1,0,140,177,0,1,162,1,0,2,1,3,0 212 | 57,1,2,128,229,0,0,150,0,0.4,1,1,3,0 213 | 61,1,0,120,260,0,1,140,1,3.6,1,1,3,0 214 | 39,1,0,118,219,0,1,140,0,1.2,1,0,3,0 215 | 61,0,0,145,307,0,0,146,1,1,1,0,3,0 216 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 217 | 43,0,0,132,341,1,0,136,1,3,1,0,3,0 218 | 62,0,2,130,263,0,1,97,0,1.2,1,1,3,0 219 | 63,1,0,130,330,1,0,132,1,1.8,2,3,3,0 220 | 65,1,0,135,254,0,0,127,0,2.8,1,1,3,0 221 | 48,1,0,130,256,1,0,150,1,0,2,2,3,0 222 | 63,0,0,150,407,0,0,154,0,4,1,3,3,0 223 | 55,1,0,140,217,0,1,111,1,5.6,0,0,3,0 224 | 65,1,3,138,282,1,0,174,0,1.4,1,1,2,0 225 | 56,0,0,200,288,1,0,133,1,4,0,2,3,0 226 | 54,1,0,110,239,0,1,126,1,2.8,1,1,3,0 227 | 70,1,0,145,174,0,1,125,1,2.6,0,0,3,0 228 | 62,1,1,120,281,0,0,103,0,1.4,1,1,3,0 229 | 35,1,0,120,198,0,1,130,1,1.6,1,0,3,0 230 | 59,1,3,170,288,0,0,159,0,0.2,1,0,3,0 231 | 64,1,2,125,309,0,1,131,1,1.8,1,0,3,0 232 | 47,1,2,108,243,0,1,152,0,0,2,0,2,0 233 | 57,1,0,165,289,1,0,124,0,1,1,3,3,0 234 | 55,1,0,160,289,0,0,145,1,0.8,1,1,3,0 235 | 64,1,0,120,246,0,0,96,1,2.2,0,1,2,0 236 | 70,1,0,130,322,0,0,109,0,2.4,1,3,2,0 237 | 51,1,0,140,299,0,1,173,1,1.6,2,0,3,0 238 | 58,1,0,125,300,0,0,171,0,0,2,2,3,0 239 | 60,1,0,140,293,0,0,170,0,1.2,1,2,3,0 240 | 77,1,0,125,304,0,0,162,1,0,2,3,2,0 241 | 35,1,0,126,282,0,0,156,1,0,2,0,3,0 242 | 70,1,2,160,269,0,1,112,1,2.9,1,1,3,0 243 | 59,0,0,174,249,0,1,143,1,0,1,0,2,0 244 | 64,1,0,145,212,0,0,132,0,2,1,2,1,0 245 | 57,1,0,152,274,0,1,88,1,1.2,1,1,3,0 246 | 56,1,0,132,184,0,0,105,1,2.1,1,1,1,0 247 | 48,1,0,124,274,0,0,166,0,0.5,1,0,3,0 248 | 56,0,0,134,409,0,0,150,1,1.9,1,2,3,0 249 | 66,1,1,160,246,0,1,120,1,0,1,3,1,0 250 | 54,1,1,192,283,0,0,195,0,0,2,1,3,0 251 | 69,1,2,140,254,0,0,146,0,2,1,3,3,0 252 | 51,1,0,140,298,0,1,122,1,4.2,1,3,3,0 253 | 43,1,0,132,247,1,0,143,1,0.1,1,4,3,0 254 | 62,0,0,138,294,1,1,106,0,1.9,1,3,2,0 255 | 67,1,0,100,299,0,0,125,1,0.9,1,2,2,0 256 | 59,1,3,160,273,0,0,125,0,0,2,0,2,0 257 | 45,1,0,142,309,0,0,147,1,0,1,3,3,0 258 | 58,1,0,128,259,0,0,130,1,3,1,2,3,0 259 | 50,1,0,144,200,0,0,126,1,0.9,1,0,3,0 260 | 62,0,0,150,244,0,1,154,1,1.4,1,0,2,0 261 | 38,1,3,120,231,0,1,182,1,3.8,1,0,3,0 262 | 66,0,0,178,228,1,1,165,1,1,1,2,3,0 263 | 52,1,0,112,230,0,1,160,0,0,2,1,2,0 264 | 53,1,0,123,282,0,1,95,1,2,1,2,3,0 265 | 63,0,0,108,269,0,1,169,1,1.8,1,2,2,0 266 | 54,1,0,110,206,0,0,108,1,0,1,1,2,0 267 | 66,1,0,112,212,0,0,132,1,0.1,2,1,2,0 268 | 55,0,0,180,327,0,2,117,1,3.4,1,0,2,0 269 | 49,1,2,118,149,0,0,126,0,0.8,2,3,2,0 270 | 54,1,0,122,286,0,0,116,1,3.2,1,2,2,0 271 | 56,1,0,130,283,1,0,103,1,1.6,0,0,3,0 272 | 46,1,0,120,249,0,0,144,0,0.8,2,0,3,0 273 | 61,1,3,134,234,0,1,145,0,2.6,1,2,2,0 274 | 67,1,0,120,237,0,1,71,0,1,1,0,2,0 275 | 58,1,0,100,234,0,1,156,0,0.1,2,1,3,0 276 | 47,1,0,110,275,0,0,118,1,1,1,1,2,0 277 | 52,1,0,125,212,0,1,168,0,1,2,2,3,0 278 | 58,1,0,146,218,0,1,105,0,2,1,1,3,0 279 | 57,1,1,124,261,0,1,141,0,0.3,2,0,3,0 280 | 58,0,1,136,319,1,0,152,0,0,2,2,2,0 281 | 61,1,0,138,166,0,0,125,1,3.6,1,1,2,0 282 | 42,1,0,136,315,0,1,125,1,1.8,1,0,1,0 283 | 52,1,0,128,204,1,1,156,1,1,1,0,0,0 284 | 59,1,2,126,218,1,1,134,0,2.2,1,1,1,0 285 | 40,1,0,152,223,0,1,181,0,0,2,0,3,0 286 | 61,1,0,140,207,0,0,138,1,1.9,2,1,3,0 287 | 46,1,0,140,311,0,1,120,1,1.8,1,2,3,0 288 | 59,1,3,134,204,0,1,162,0,0.8,2,2,2,0 289 | 57,1,1,154,232,0,0,164,0,0,2,1,2,0 290 | 57,1,0,110,335,0,1,143,1,3,1,1,3,0 291 | 55,0,0,128,205,0,2,130,1,2,1,1,3,0 292 | 61,1,0,148,203,0,1,161,0,0,2,1,3,0 293 | 58,1,0,114,318,0,2,140,0,4.4,0,3,1,0 294 | 58,0,0,170,225,1,0,146,1,2.8,1,2,1,0 295 | 67,1,2,152,212,0,0,150,0,0.8,1,0,3,0 296 | 44,1,0,120,169,0,1,144,1,2.8,0,0,1,0 297 | 63,1,0,140,187,0,0,144,1,4,2,2,3,0 298 | 63,0,0,124,197,0,1,136,1,0,1,0,2,0 299 | 59,1,0,164,176,1,0,90,0,1,1,2,1,0 300 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 301 | 45,1,3,110,264,0,1,132,0,1.2,1,0,3,0 302 | 68,1,0,144,193,1,1,141,0,3.4,1,2,3,0 303 | 57,1,0,130,131,0,1,115,1,1.2,1,1,3,0 304 | 57,0,1,130,236,0,0,174,0,0,1,1,2,0 305 | -------------------------------------------------------------------------------- /uci_heart_disease/Data/heart.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 63,1,3,145,233,1,0,150,0,2.3,0,0,1,1 3 | 37,1,2,130,250,0,1,187,0,3.5,0,0,2,1 4 | 41,0,1,130,204,0,0,172,0,1.4,2,0,2,1 5 | 56,1,1,120,236,0,1,178,0,0.8,2,0,2,1 6 | 57,0,0,120,354,0,1,163,1,0.6,2,0,2,1 7 | 57,1,0,140,192,0,1,148,0,0.4,1,0,1,1 8 | 56,0,1,140,294,0,0,153,0,1.3,1,0,2,1 9 | 44,1,1,120,263,0,1,173,0,0,2,0,3,1 10 | 52,1,2,172,199,1,1,162,0,0.5,2,0,3,1 11 | 57,1,2,150,168,0,1,174,0,1.6,2,0,2,1 12 | 54,1,0,140,239,0,1,160,0,1.2,2,0,2,1 13 | 48,0,2,130,275,0,1,139,0,0.2,2,0,2,1 14 | 49,1,1,130,266,0,1,171,0,0.6,2,0,2,1 15 | 64,1,3,110,211,0,0,144,1,1.8,1,0,2,1 16 | 58,0,3,150,283,1,0,162,0,1,2,0,2,1 17 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 18 | 58,0,2,120,340,0,1,172,0,0,2,0,2,1 19 | 66,0,3,150,226,0,1,114,0,2.6,0,0,2,1 20 | 43,1,0,150,247,0,1,171,0,1.5,2,0,2,1 21 | 69,0,3,140,239,0,1,151,0,1.8,2,2,2,1 22 | 59,1,0,135,234,0,1,161,0,0.5,1,0,3,1 23 | 44,1,2,130,233,0,1,179,1,0.4,2,0,2,1 24 | 42,1,0,140,226,0,1,178,0,0,2,0,2,1 25 | 61,1,2,150,243,1,1,137,1,1,1,0,2,1 26 | 40,1,3,140,199,0,1,178,1,1.4,2,0,3,1 27 | 71,0,1,160,302,0,1,162,0,0.4,2,2,2,1 28 | 59,1,2,150,212,1,1,157,0,1.6,2,0,2,1 29 | 51,1,2,110,175,0,1,123,0,0.6,2,0,2,1 30 | 65,0,2,140,417,1,0,157,0,0.8,2,1,2,1 31 | 53,1,2,130,197,1,0,152,0,1.2,0,0,2,1 32 | 41,0,1,105,198,0,1,168,0,0,2,1,2,1 33 | 65,1,0,120,177,0,1,140,0,0.4,2,0,3,1 34 | 44,1,1,130,219,0,0,188,0,0,2,0,2,1 35 | 54,1,2,125,273,0,0,152,0,0.5,0,1,2,1 36 | 51,1,3,125,213,0,0,125,1,1.4,2,1,2,1 37 | 46,0,2,142,177,0,0,160,1,1.4,0,0,2,1 38 | 54,0,2,135,304,1,1,170,0,0,2,0,2,1 39 | 54,1,2,150,232,0,0,165,0,1.6,2,0,3,1 40 | 65,0,2,155,269,0,1,148,0,0.8,2,0,2,1 41 | 65,0,2,160,360,0,0,151,0,0.8,2,0,2,1 42 | 51,0,2,140,308,0,0,142,0,1.5,2,1,2,1 43 | 48,1,1,130,245,0,0,180,0,0.2,1,0,2,1 44 | 45,1,0,104,208,0,0,148,1,3,1,0,2,1 45 | 53,0,0,130,264,0,0,143,0,0.4,1,0,2,1 46 | 39,1,2,140,321,0,0,182,0,0,2,0,2,1 47 | 52,1,1,120,325,0,1,172,0,0.2,2,0,2,1 48 | 44,1,2,140,235,0,0,180,0,0,2,0,2,1 49 | 47,1,2,138,257,0,0,156,0,0,2,0,2,1 50 | 53,0,2,128,216,0,0,115,0,0,2,0,0,1 51 | 53,0,0,138,234,0,0,160,0,0,2,0,2,1 52 | 51,0,2,130,256,0,0,149,0,0.5,2,0,2,1 53 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 54 | 62,1,2,130,231,0,1,146,0,1.8,1,3,3,1 55 | 44,0,2,108,141,0,1,175,0,0.6,1,0,2,1 56 | 63,0,2,135,252,0,0,172,0,0,2,0,2,1 57 | 52,1,1,134,201,0,1,158,0,0.8,2,1,2,1 58 | 48,1,0,122,222,0,0,186,0,0,2,0,2,1 59 | 45,1,0,115,260,0,0,185,0,0,2,0,2,1 60 | 34,1,3,118,182,0,0,174,0,0,2,0,2,1 61 | 57,0,0,128,303,0,0,159,0,0,2,1,2,1 62 | 71,0,2,110,265,1,0,130,0,0,2,1,2,1 63 | 54,1,1,108,309,0,1,156,0,0,2,0,3,1 64 | 52,1,3,118,186,0,0,190,0,0,1,0,1,1 65 | 41,1,1,135,203,0,1,132,0,0,1,0,1,1 66 | 58,1,2,140,211,1,0,165,0,0,2,0,2,1 67 | 35,0,0,138,183,0,1,182,0,1.4,2,0,2,1 68 | 51,1,2,100,222,0,1,143,1,1.2,1,0,2,1 69 | 45,0,1,130,234,0,0,175,0,0.6,1,0,2,1 70 | 44,1,1,120,220,0,1,170,0,0,2,0,2,1 71 | 62,0,0,124,209,0,1,163,0,0,2,0,2,1 72 | 54,1,2,120,258,0,0,147,0,0.4,1,0,3,1 73 | 51,1,2,94,227,0,1,154,1,0,2,1,3,1 74 | 29,1,1,130,204,0,0,202,0,0,2,0,2,1 75 | 51,1,0,140,261,0,0,186,1,0,2,0,2,1 76 | 43,0,2,122,213,0,1,165,0,0.2,1,0,2,1 77 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 78 | 51,1,2,125,245,1,0,166,0,2.4,1,0,2,1 79 | 59,1,1,140,221,0,1,164,1,0,2,0,2,1 80 | 52,1,1,128,205,1,1,184,0,0,2,0,2,1 81 | 58,1,2,105,240,0,0,154,1,0.6,1,0,3,1 82 | 41,1,2,112,250,0,1,179,0,0,2,0,2,1 83 | 45,1,1,128,308,0,0,170,0,0,2,0,2,1 84 | 60,0,2,102,318,0,1,160,0,0,2,1,2,1 85 | 52,1,3,152,298,1,1,178,0,1.2,1,0,3,1 86 | 42,0,0,102,265,0,0,122,0,0.6,1,0,2,1 87 | 67,0,2,115,564,0,0,160,0,1.6,1,0,3,1 88 | 68,1,2,118,277,0,1,151,0,1,2,1,3,1 89 | 46,1,1,101,197,1,1,156,0,0,2,0,3,1 90 | 54,0,2,110,214,0,1,158,0,1.6,1,0,2,1 91 | 58,0,0,100,248,0,0,122,0,1,1,0,2,1 92 | 48,1,2,124,255,1,1,175,0,0,2,2,2,1 93 | 57,1,0,132,207,0,1,168,1,0,2,0,3,1 94 | 52,1,2,138,223,0,1,169,0,0,2,4,2,1 95 | 54,0,1,132,288,1,0,159,1,0,2,1,2,1 96 | 45,0,1,112,160,0,1,138,0,0,1,0,2,1 97 | 53,1,0,142,226,0,0,111,1,0,2,0,3,1 98 | 62,0,0,140,394,0,0,157,0,1.2,1,0,2,1 99 | 52,1,0,108,233,1,1,147,0,0.1,2,3,3,1 100 | 43,1,2,130,315,0,1,162,0,1.9,2,1,2,1 101 | 53,1,2,130,246,1,0,173,0,0,2,3,2,1 102 | 42,1,3,148,244,0,0,178,0,0.8,2,2,2,1 103 | 59,1,3,178,270,0,0,145,0,4.2,0,0,3,1 104 | 63,0,1,140,195,0,1,179,0,0,2,2,2,1 105 | 42,1,2,120,240,1,1,194,0,0.8,0,0,3,1 106 | 50,1,2,129,196,0,1,163,0,0,2,0,2,1 107 | 68,0,2,120,211,0,0,115,0,1.5,1,0,2,1 108 | 69,1,3,160,234,1,0,131,0,0.1,1,1,2,1 109 | 45,0,0,138,236,0,0,152,1,0.2,1,0,2,1 110 | 50,0,1,120,244,0,1,162,0,1.1,2,0,2,1 111 | 50,0,0,110,254,0,0,159,0,0,2,0,2,1 112 | 64,0,0,180,325,0,1,154,1,0,2,0,2,1 113 | 57,1,2,150,126,1,1,173,0,0.2,2,1,3,1 114 | 64,0,2,140,313,0,1,133,0,0.2,2,0,3,1 115 | 43,1,0,110,211,0,1,161,0,0,2,0,3,1 116 | 55,1,1,130,262,0,1,155,0,0,2,0,2,1 117 | 37,0,2,120,215,0,1,170,0,0,2,0,2,1 118 | 41,1,2,130,214,0,0,168,0,2,1,0,2,1 119 | 56,1,3,120,193,0,0,162,0,1.9,1,0,3,1 120 | 46,0,1,105,204,0,1,172,0,0,2,0,2,1 121 | 46,0,0,138,243,0,0,152,1,0,1,0,2,1 122 | 64,0,0,130,303,0,1,122,0,2,1,2,2,1 123 | 59,1,0,138,271,0,0,182,0,0,2,0,2,1 124 | 41,0,2,112,268,0,0,172,1,0,2,0,2,1 125 | 54,0,2,108,267,0,0,167,0,0,2,0,2,1 126 | 39,0,2,94,199,0,1,179,0,0,2,0,2,1 127 | 34,0,1,118,210,0,1,192,0,0.7,2,0,2,1 128 | 47,1,0,112,204,0,1,143,0,0.1,2,0,2,1 129 | 67,0,2,152,277,0,1,172,0,0,2,1,2,1 130 | 52,0,2,136,196,0,0,169,0,0.1,1,0,2,1 131 | 74,0,1,120,269,0,0,121,1,0.2,2,1,2,1 132 | 54,0,2,160,201,0,1,163,0,0,2,1,2,1 133 | 49,0,1,134,271,0,1,162,0,0,1,0,2,1 134 | 42,1,1,120,295,0,1,162,0,0,2,0,2,1 135 | 41,1,1,110,235,0,1,153,0,0,2,0,2,1 136 | 41,0,1,126,306,0,1,163,0,0,2,0,2,1 137 | 49,0,0,130,269,0,1,163,0,0,2,0,2,1 138 | 60,0,2,120,178,1,1,96,0,0,2,0,2,1 139 | 62,1,1,128,208,1,0,140,0,0,2,0,2,1 140 | 57,1,0,110,201,0,1,126,1,1.5,1,0,1,1 141 | 64,1,0,128,263,0,1,105,1,0.2,1,1,3,1 142 | 51,0,2,120,295,0,0,157,0,0.6,2,0,2,1 143 | 43,1,0,115,303,0,1,181,0,1.2,1,0,2,1 144 | 42,0,2,120,209,0,1,173,0,0,1,0,2,1 145 | 67,0,0,106,223,0,1,142,0,0.3,2,2,2,1 146 | 76,0,2,140,197,0,2,116,0,1.1,1,0,2,1 147 | 70,1,1,156,245,0,0,143,0,0,2,0,2,1 148 | 44,0,2,118,242,0,1,149,0,0.3,1,1,2,1 149 | 60,0,3,150,240,0,1,171,0,0.9,2,0,2,1 150 | 44,1,2,120,226,0,1,169,0,0,2,0,2,1 151 | 42,1,2,130,180,0,1,150,0,0,2,0,2,1 152 | 66,1,0,160,228,0,0,138,0,2.3,2,0,1,1 153 | 71,0,0,112,149,0,1,125,0,1.6,1,0,2,1 154 | 64,1,3,170,227,0,0,155,0,0.6,1,0,3,1 155 | 66,0,2,146,278,0,0,152,0,0,1,1,2,1 156 | 39,0,2,138,220,0,1,152,0,0,1,0,2,1 157 | 58,0,0,130,197,0,1,131,0,0.6,1,0,2,1 158 | 47,1,2,130,253,0,1,179,0,0,2,0,2,1 159 | 35,1,1,122,192,0,1,174,0,0,2,0,2,1 160 | 58,1,1,125,220,0,1,144,0,0.4,1,4,3,1 161 | 56,1,1,130,221,0,0,163,0,0,2,0,3,1 162 | 56,1,1,120,240,0,1,169,0,0,0,0,2,1 163 | 55,0,1,132,342,0,1,166,0,1.2,2,0,2,1 164 | 41,1,1,120,157,0,1,182,0,0,2,0,2,1 165 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 166 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 167 | 67,1,0,160,286,0,0,108,1,1.5,1,3,2,0 168 | 67,1,0,120,229,0,0,129,1,2.6,1,2,3,0 169 | 62,0,0,140,268,0,0,160,0,3.6,0,2,2,0 170 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 171 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 172 | 56,1,2,130,256,1,0,142,1,0.6,1,1,1,0 173 | 48,1,1,110,229,0,1,168,0,1,0,0,3,0 174 | 58,1,1,120,284,0,0,160,0,1.8,1,0,2,0 175 | 58,1,2,132,224,0,0,173,0,3.2,2,2,3,0 176 | 60,1,0,130,206,0,0,132,1,2.4,1,2,3,0 177 | 40,1,0,110,167,0,0,114,1,2,1,0,3,0 178 | 60,1,0,117,230,1,1,160,1,1.4,2,2,3,0 179 | 64,1,2,140,335,0,1,158,0,0,2,0,2,0 180 | 43,1,0,120,177,0,0,120,1,2.5,1,0,3,0 181 | 57,1,0,150,276,0,0,112,1,0.6,1,1,1,0 182 | 55,1,0,132,353,0,1,132,1,1.2,1,1,3,0 183 | 65,0,0,150,225,0,0,114,0,1,1,3,3,0 184 | 61,0,0,130,330,0,0,169,0,0,2,0,2,0 185 | 58,1,2,112,230,0,0,165,0,2.5,1,1,3,0 186 | 50,1,0,150,243,0,0,128,0,2.6,1,0,3,0 187 | 44,1,0,112,290,0,0,153,0,0,2,1,2,0 188 | 60,1,0,130,253,0,1,144,1,1.4,2,1,3,0 189 | 54,1,0,124,266,0,0,109,1,2.2,1,1,3,0 190 | 50,1,2,140,233,0,1,163,0,0.6,1,1,3,0 191 | 41,1,0,110,172,0,0,158,0,0,2,0,3,0 192 | 51,0,0,130,305,0,1,142,1,1.2,1,0,3,0 193 | 58,1,0,128,216,0,0,131,1,2.2,1,3,3,0 194 | 54,1,0,120,188,0,1,113,0,1.4,1,1,3,0 195 | 60,1,0,145,282,0,0,142,1,2.8,1,2,3,0 196 | 60,1,2,140,185,0,0,155,0,3,1,0,2,0 197 | 59,1,0,170,326,0,0,140,1,3.4,0,0,3,0 198 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 199 | 67,1,0,125,254,1,1,163,0,0.2,1,2,3,0 200 | 62,1,0,120,267,0,1,99,1,1.8,1,2,3,0 201 | 65,1,0,110,248,0,0,158,0,0.6,2,2,1,0 202 | 44,1,0,110,197,0,0,177,0,0,2,1,2,0 203 | 60,1,0,125,258,0,0,141,1,2.8,1,1,3,0 204 | 58,1,0,150,270,0,0,111,1,0.8,2,0,3,0 205 | 68,1,2,180,274,1,0,150,1,1.6,1,0,3,0 206 | 62,0,0,160,164,0,0,145,0,6.2,0,3,3,0 207 | 52,1,0,128,255,0,1,161,1,0,2,1,3,0 208 | 59,1,0,110,239,0,0,142,1,1.2,1,1,3,0 209 | 60,0,0,150,258,0,0,157,0,2.6,1,2,3,0 210 | 49,1,2,120,188,0,1,139,0,2,1,3,3,0 211 | 59,1,0,140,177,0,1,162,1,0,2,1,3,0 212 | 57,1,2,128,229,0,0,150,0,0.4,1,1,3,0 213 | 61,1,0,120,260,0,1,140,1,3.6,1,1,3,0 214 | 39,1,0,118,219,0,1,140,0,1.2,1,0,3,0 215 | 61,0,0,145,307,0,0,146,1,1,1,0,3,0 216 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 217 | 43,0,0,132,341,1,0,136,1,3,1,0,3,0 218 | 62,0,2,130,263,0,1,97,0,1.2,1,1,3,0 219 | 63,1,0,130,330,1,0,132,1,1.8,2,3,3,0 220 | 65,1,0,135,254,0,0,127,0,2.8,1,1,3,0 221 | 48,1,0,130,256,1,0,150,1,0,2,2,3,0 222 | 63,0,0,150,407,0,0,154,0,4,1,3,3,0 223 | 55,1,0,140,217,0,1,111,1,5.6,0,0,3,0 224 | 65,1,3,138,282,1,0,174,0,1.4,1,1,2,0 225 | 56,0,0,200,288,1,0,133,1,4,0,2,3,0 226 | 54,1,0,110,239,0,1,126,1,2.8,1,1,3,0 227 | 70,1,0,145,174,0,1,125,1,2.6,0,0,3,0 228 | 62,1,1,120,281,0,0,103,0,1.4,1,1,3,0 229 | 35,1,0,120,198,0,1,130,1,1.6,1,0,3,0 230 | 59,1,3,170,288,0,0,159,0,0.2,1,0,3,0 231 | 64,1,2,125,309,0,1,131,1,1.8,1,0,3,0 232 | 47,1,2,108,243,0,1,152,0,0,2,0,2,0 233 | 57,1,0,165,289,1,0,124,0,1,1,3,3,0 234 | 55,1,0,160,289,0,0,145,1,0.8,1,1,3,0 235 | 64,1,0,120,246,0,0,96,1,2.2,0,1,2,0 236 | 70,1,0,130,322,0,0,109,0,2.4,1,3,2,0 237 | 51,1,0,140,299,0,1,173,1,1.6,2,0,3,0 238 | 58,1,0,125,300,0,0,171,0,0,2,2,3,0 239 | 60,1,0,140,293,0,0,170,0,1.2,1,2,3,0 240 | 77,1,0,125,304,0,0,162,1,0,2,3,2,0 241 | 35,1,0,126,282,0,0,156,1,0,2,0,3,0 242 | 70,1,2,160,269,0,1,112,1,2.9,1,1,3,0 243 | 59,0,0,174,249,0,1,143,1,0,1,0,2,0 244 | 64,1,0,145,212,0,0,132,0,2,1,2,1,0 245 | 57,1,0,152,274,0,1,88,1,1.2,1,1,3,0 246 | 56,1,0,132,184,0,0,105,1,2.1,1,1,1,0 247 | 48,1,0,124,274,0,0,166,0,0.5,1,0,3,0 248 | 56,0,0,134,409,0,0,150,1,1.9,1,2,3,0 249 | 66,1,1,160,246,0,1,120,1,0,1,3,1,0 250 | 54,1,1,192,283,0,0,195,0,0,2,1,3,0 251 | 69,1,2,140,254,0,0,146,0,2,1,3,3,0 252 | 51,1,0,140,298,0,1,122,1,4.2,1,3,3,0 253 | 43,1,0,132,247,1,0,143,1,0.1,1,4,3,0 254 | 62,0,0,138,294,1,1,106,0,1.9,1,3,2,0 255 | 67,1,0,100,299,0,0,125,1,0.9,1,2,2,0 256 | 59,1,3,160,273,0,0,125,0,0,2,0,2,0 257 | 45,1,0,142,309,0,0,147,1,0,1,3,3,0 258 | 58,1,0,128,259,0,0,130,1,3,1,2,3,0 259 | 50,1,0,144,200,0,0,126,1,0.9,1,0,3,0 260 | 62,0,0,150,244,0,1,154,1,1.4,1,0,2,0 261 | 38,1,3,120,231,0,1,182,1,3.8,1,0,3,0 262 | 66,0,0,178,228,1,1,165,1,1,1,2,3,0 263 | 52,1,0,112,230,0,1,160,0,0,2,1,2,0 264 | 53,1,0,123,282,0,1,95,1,2,1,2,3,0 265 | 63,0,0,108,269,0,1,169,1,1.8,1,2,2,0 266 | 54,1,0,110,206,0,0,108,1,0,1,1,2,0 267 | 66,1,0,112,212,0,0,132,1,0.1,2,1,2,0 268 | 55,0,0,180,327,0,2,117,1,3.4,1,0,2,0 269 | 49,1,2,118,149,0,0,126,0,0.8,2,3,2,0 270 | 54,1,0,122,286,0,0,116,1,3.2,1,2,2,0 271 | 56,1,0,130,283,1,0,103,1,1.6,0,0,3,0 272 | 46,1,0,120,249,0,0,144,0,0.8,2,0,3,0 273 | 61,1,3,134,234,0,1,145,0,2.6,1,2,2,0 274 | 67,1,0,120,237,0,1,71,0,1,1,0,2,0 275 | 58,1,0,100,234,0,1,156,0,0.1,2,1,3,0 276 | 47,1,0,110,275,0,0,118,1,1,1,1,2,0 277 | 52,1,0,125,212,0,1,168,0,1,2,2,3,0 278 | 58,1,0,146,218,0,1,105,0,2,1,1,3,0 279 | 57,1,1,124,261,0,1,141,0,0.3,2,0,3,0 280 | 58,0,1,136,319,1,0,152,0,0,2,2,2,0 281 | 61,1,0,138,166,0,0,125,1,3.6,1,1,2,0 282 | 42,1,0,136,315,0,1,125,1,1.8,1,0,1,0 283 | 52,1,0,128,204,1,1,156,1,1,1,0,0,0 284 | 59,1,2,126,218,1,1,134,0,2.2,1,1,1,0 285 | 40,1,0,152,223,0,1,181,0,0,2,0,3,0 286 | 61,1,0,140,207,0,0,138,1,1.9,2,1,3,0 287 | 46,1,0,140,311,0,1,120,1,1.8,1,2,3,0 288 | 59,1,3,134,204,0,1,162,0,0.8,2,2,2,0 289 | 57,1,1,154,232,0,0,164,0,0,2,1,2,0 290 | 57,1,0,110,335,0,1,143,1,3,1,1,3,0 291 | 55,0,0,128,205,0,2,130,1,2,1,1,3,0 292 | 61,1,0,148,203,0,1,161,0,0,2,1,3,0 293 | 58,1,0,114,318,0,2,140,0,4.4,0,3,1,0 294 | 58,0,0,170,225,1,0,146,1,2.8,1,2,1,0 295 | 67,1,2,152,212,0,0,150,0,0.8,1,0,3,0 296 | 44,1,0,120,169,0,1,144,1,2.8,0,0,1,0 297 | 63,1,0,140,187,0,0,144,1,4,2,2,3,0 298 | 63,0,0,124,197,0,1,136,1,0,1,0,2,0 299 | 59,1,0,164,176,1,0,90,0,1,1,2,1,0 300 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 301 | 45,1,3,110,264,0,1,132,0,1.2,1,0,3,0 302 | 68,1,0,144,193,1,1,141,0,3.4,1,2,3,0 303 | 57,1,0,130,131,0,1,115,1,1.2,1,1,3,0 304 | 57,0,1,130,236,0,0,174,0,0,1,1,2,0 305 | -------------------------------------------------------------------------------- /exception handling and logging/Data/heart.csv: -------------------------------------------------------------------------------- 1 | age,sex,chest_pain_type,resting_bp,cholestoral,fasting_blood_sugar,restecg,max_hr,exang,oldpeak,slope,num_major_vessels,thal,target 2 | 63,1,3,145,233,1,0,150,0,2.3,0,0,1,1 3 | 37,1,2,130,250,0,1,187,0,3.5,0,0,2,1 4 | 41,0,1,130,204,0,0,172,0,1.4,2,0,2,1 5 | 56,1,1,120,236,0,1,178,0,0.8,2,0,2,1 6 | 57,0,0,120,354,0,1,163,1,0.6,2,0,2,1 7 | 57,1,0,140,192,0,1,148,0,0.4,1,0,1,1 8 | 56,0,1,140,294,0,0,153,0,1.3,1,0,2,1 9 | 44,1,1,120,263,0,1,173,0,0,2,0,3,1 10 | 52,1,2,172,199,1,1,162,0,0.5,2,0,3,1 11 | 57,1,2,150,168,0,1,174,0,1.6,2,0,2,1 12 | 54,1,0,140,239,0,1,160,0,1.2,2,0,2,1 13 | 48,0,2,130,275,0,1,139,0,0.2,2,0,2,1 14 | 49,1,1,130,266,0,1,171,0,0.6,2,0,2,1 15 | 64,1,3,110,211,0,0,144,1,1.8,1,0,2,1 16 | 58,0,3,150,283,1,0,162,0,1,2,0,2,1 17 | 50,0,2,120,219,0,1,158,0,1.6,1,0,2,1 18 | 58,0,2,120,340,0,1,172,0,0,2,0,2,1 19 | 66,0,3,150,226,0,1,114,0,2.6,0,0,2,1 20 | 43,1,0,150,247,0,1,171,0,1.5,2,0,2,1 21 | 69,0,3,140,239,0,1,151,0,1.8,2,2,2,1 22 | 59,1,0,135,234,0,1,161,0,0.5,1,0,3,1 23 | 44,1,2,130,233,0,1,179,1,0.4,2,0,2,1 24 | 42,1,0,140,226,0,1,178,0,0,2,0,2,1 25 | 61,1,2,150,243,1,1,137,1,1,1,0,2,1 26 | 40,1,3,140,199,0,1,178,1,1.4,2,0,3,1 27 | 71,0,1,160,302,0,1,162,0,0.4,2,2,2,1 28 | 59,1,2,150,212,1,1,157,0,1.6,2,0,2,1 29 | 51,1,2,110,175,0,1,123,0,0.6,2,0,2,1 30 | 65,0,2,140,417,1,0,157,0,0.8,2,1,2,1 31 | 53,1,2,130,197,1,0,152,0,1.2,0,0,2,1 32 | 41,0,1,105,198,0,1,168,0,0,2,1,2,1 33 | 65,1,0,120,177,0,1,140,0,0.4,2,0,3,1 34 | 44,1,1,130,219,0,0,188,0,0,2,0,2,1 35 | 54,1,2,125,273,0,0,152,0,0.5,0,1,2,1 36 | 51,1,3,125,213,0,0,125,1,1.4,2,1,2,1 37 | 46,0,2,142,177,0,0,160,1,1.4,0,0,2,1 38 | 54,0,2,135,304,1,1,170,0,0,2,0,2,1 39 | 54,1,2,150,232,0,0,165,0,1.6,2,0,3,1 40 | 65,0,2,155,269,0,1,148,0,0.8,2,0,2,1 41 | 65,0,2,160,360,0,0,151,0,0.8,2,0,2,1 42 | 51,0,2,140,308,0,0,142,0,1.5,2,1,2,1 43 | 48,1,1,130,245,0,0,180,0,0.2,1,0,2,1 44 | 45,1,0,104,208,0,0,148,1,3,1,0,2,1 45 | 53,0,0,130,264,0,0,143,0,0.4,1,0,2,1 46 | 39,1,2,140,321,0,0,182,0,0,2,0,2,1 47 | 52,1,1,120,325,0,1,172,0,0.2,2,0,2,1 48 | 44,1,2,140,235,0,0,180,0,0,2,0,2,1 49 | 47,1,2,138,257,0,0,156,0,0,2,0,2,1 50 | 53,0,2,128,216,0,0,115,0,0,2,0,0,1 51 | 53,0,0,138,234,0,0,160,0,0,2,0,2,1 52 | 51,0,2,130,256,0,0,149,0,0.5,2,0,2,1 53 | 66,1,0,120,302,0,0,151,0,0.4,1,0,2,1 54 | 62,1,2,130,231,0,1,146,0,1.8,1,3,3,1 55 | 44,0,2,108,141,0,1,175,0,0.6,1,0,2,1 56 | 63,0,2,135,252,0,0,172,0,0,2,0,2,1 57 | 52,1,1,134,201,0,1,158,0,0.8,2,1,2,1 58 | 48,1,0,122,222,0,0,186,0,0,2,0,2,1 59 | 45,1,0,115,260,0,0,185,0,0,2,0,2,1 60 | 34,1,3,118,182,0,0,174,0,0,2,0,2,1 61 | 57,0,0,128,303,0,0,159,0,0,2,1,2,1 62 | 71,0,2,110,265,1,0,130,0,0,2,1,2,1 63 | 54,1,1,108,309,0,1,156,0,0,2,0,3,1 64 | 52,1,3,118,186,0,0,190,0,0,1,0,1,1 65 | 41,1,1,135,203,0,1,132,0,0,1,0,1,1 66 | 58,1,2,140,211,1,0,165,0,0,2,0,2,1 67 | 35,0,0,138,183,0,1,182,0,1.4,2,0,2,1 68 | 51,1,2,100,222,0,1,143,1,1.2,1,0,2,1 69 | 45,0,1,130,234,0,0,175,0,0.6,1,0,2,1 70 | 44,1,1,120,220,0,1,170,0,0,2,0,2,1 71 | 62,0,0,124,209,0,1,163,0,0,2,0,2,1 72 | 54,1,2,120,258,0,0,147,0,0.4,1,0,3,1 73 | 51,1,2,94,227,0,1,154,1,0,2,1,3,1 74 | 29,1,1,130,204,0,0,202,0,0,2,0,2,1 75 | 51,1,0,140,261,0,0,186,1,0,2,0,2,1 76 | 43,0,2,122,213,0,1,165,0,0.2,1,0,2,1 77 | 55,0,1,135,250,0,0,161,0,1.4,1,0,2,1 78 | 51,1,2,125,245,1,0,166,0,2.4,1,0,2,1 79 | 59,1,1,140,221,0,1,164,1,0,2,0,2,1 80 | 52,1,1,128,205,1,1,184,0,0,2,0,2,1 81 | 58,1,2,105,240,0,0,154,1,0.6,1,0,3,1 82 | 41,1,2,112,250,0,1,179,0,0,2,0,2,1 83 | 45,1,1,128,308,0,0,170,0,0,2,0,2,1 84 | 60,0,2,102,318,0,1,160,0,0,2,1,2,1 85 | 52,1,3,152,298,1,1,178,0,1.2,1,0,3,1 86 | 42,0,0,102,265,0,0,122,0,0.6,1,0,2,1 87 | 67,0,2,115,564,0,0,160,0,1.6,1,0,3,1 88 | 68,1,2,118,277,0,1,151,0,1,2,1,3,1 89 | 46,1,1,101,197,1,1,156,0,0,2,0,3,1 90 | 54,0,2,110,214,0,1,158,0,1.6,1,0,2,1 91 | 58,0,0,100,248,0,0,122,0,1,1,0,2,1 92 | 48,1,2,124,255,1,1,175,0,0,2,2,2,1 93 | 57,1,0,132,207,0,1,168,1,0,2,0,3,1 94 | 52,1,2,138,223,0,1,169,0,0,2,4,2,1 95 | 54,0,1,132,288,1,0,159,1,0,2,1,2,1 96 | 45,0,1,112,160,0,1,138,0,0,1,0,2,1 97 | 53,1,0,142,226,0,0,111,1,0,2,0,3,1 98 | 62,0,0,140,394,0,0,157,0,1.2,1,0,2,1 99 | 52,1,0,108,233,1,1,147,0,0.1,2,3,3,1 100 | 43,1,2,130,315,0,1,162,0,1.9,2,1,2,1 101 | 53,1,2,130,246,1,0,173,0,0,2,3,2,1 102 | 42,1,3,148,244,0,0,178,0,0.8,2,2,2,1 103 | 59,1,3,178,270,0,0,145,0,4.2,0,0,3,1 104 | 63,0,1,140,195,0,1,179,0,0,2,2,2,1 105 | 42,1,2,120,240,1,1,194,0,0.8,0,0,3,1 106 | 50,1,2,129,196,0,1,163,0,0,2,0,2,1 107 | 68,0,2,120,211,0,0,115,0,1.5,1,0,2,1 108 | 69,1,3,160,234,1,0,131,0,0.1,1,1,2,1 109 | 45,0,0,138,236,0,0,152,1,0.2,1,0,2,1 110 | 50,0,1,120,244,0,1,162,0,1.1,2,0,2,1 111 | 50,0,0,110,254,0,0,159,0,0,2,0,2,1 112 | 64,0,0,180,325,0,1,154,1,0,2,0,2,1 113 | 57,1,2,150,126,1,1,173,0,0.2,2,1,3,1 114 | 64,0,2,140,313,0,1,133,0,0.2,2,0,3,1 115 | 43,1,0,110,211,0,1,161,0,0,2,0,3,1 116 | 55,1,1,130,262,0,1,155,0,0,2,0,2,1 117 | 37,0,2,120,215,0,1,170,0,0,2,0,2,1 118 | 41,1,2,130,214,0,0,168,0,2,1,0,2,1 119 | 56,1,3,120,193,0,0,162,0,1.9,1,0,3,1 120 | 46,0,1,105,204,0,1,172,0,0,2,0,2,1 121 | 46,0,0,138,243,0,0,152,1,0,1,0,2,1 122 | 64,0,0,130,303,0,1,122,0,2,1,2,2,1 123 | 59,1,0,138,271,0,0,182,0,0,2,0,2,1 124 | 41,0,2,112,268,0,0,172,1,0,2,0,2,1 125 | 54,0,2,108,267,0,0,167,0,0,2,0,2,1 126 | 39,0,2,94,199,0,1,179,0,0,2,0,2,1 127 | 34,0,1,118,210,0,1,192,0,0.7,2,0,2,1 128 | 47,1,0,112,204,0,1,143,0,0.1,2,0,2,1 129 | 67,0,2,152,277,0,1,172,0,0,2,1,2,1 130 | 52,0,2,136,196,0,0,169,0,0.1,1,0,2,1 131 | 74,0,1,120,269,0,0,121,1,0.2,2,1,2,1 132 | 54,0,2,160,201,0,1,163,0,0,2,1,2,1 133 | 49,0,1,134,271,0,1,162,0,0,1,0,2,1 134 | 42,1,1,120,295,0,1,162,0,0,2,0,2,1 135 | 41,1,1,110,235,0,1,153,0,0,2,0,2,1 136 | 41,0,1,126,306,0,1,163,0,0,2,0,2,1 137 | 49,0,0,130,269,0,1,163,0,0,2,0,2,1 138 | 60,0,2,120,178,1,1,96,0,0,2,0,2,1 139 | 62,1,1,128,208,1,0,140,0,0,2,0,2,1 140 | 57,1,0,110,201,0,1,126,1,1.5,1,0,1,1 141 | 64,1,0,128,263,0,1,105,1,0.2,1,1,3,1 142 | 51,0,2,120,295,0,0,157,0,0.6,2,0,2,1 143 | 43,1,0,115,303,0,1,181,0,1.2,1,0,2,1 144 | 42,0,2,120,209,0,1,173,0,0,1,0,2,1 145 | 67,0,0,106,223,0,1,142,0,0.3,2,2,2,1 146 | 76,0,2,140,197,0,2,116,0,1.1,1,0,2,1 147 | 70,1,1,156,245,0,0,143,0,0,2,0,2,1 148 | 44,0,2,118,242,0,1,149,0,0.3,1,1,2,1 149 | 60,0,3,150,240,0,1,171,0,0.9,2,0,2,1 150 | 44,1,2,120,226,0,1,169,0,0,2,0,2,1 151 | 42,1,2,130,180,0,1,150,0,0,2,0,2,1 152 | 66,1,0,160,228,0,0,138,0,2.3,2,0,1,1 153 | 71,0,0,112,149,0,1,125,0,1.6,1,0,2,1 154 | 64,1,3,170,227,0,0,155,0,0.6,1,0,3,1 155 | 66,0,2,146,278,0,0,152,0,0,1,1,2,1 156 | 39,0,2,138,220,0,1,152,0,0,1,0,2,1 157 | 58,0,0,130,197,0,1,131,0,0.6,1,0,2,1 158 | 47,1,2,130,253,0,1,179,0,0,2,0,2,1 159 | 35,1,1,122,192,0,1,174,0,0,2,0,2,1 160 | 58,1,1,125,220,0,1,144,0,0.4,1,4,3,1 161 | 56,1,1,130,221,0,0,163,0,0,2,0,3,1 162 | 56,1,1,120,240,0,1,169,0,0,0,0,2,1 163 | 55,0,1,132,342,0,1,166,0,1.2,2,0,2,1 164 | 41,1,1,120,157,0,1,182,0,0,2,0,2,1 165 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 166 | 38,1,2,138,175,0,1,173,0,0,2,4,2,1 167 | 67,1,0,160,286,0,0,108,1,1.5,1,3,2,0 168 | 67,1,0,120,229,0,0,129,1,2.6,1,2,3,0 169 | 62,0,0,140,268,0,0,160,0,3.6,0,2,2,0 170 | 63,1,0,130,254,0,0,147,0,1.4,1,1,3,0 171 | 53,1,0,140,203,1,0,155,1,3.1,0,0,3,0 172 | 56,1,2,130,256,1,0,142,1,0.6,1,1,1,0 173 | 48,1,1,110,229,0,1,168,0,1,0,0,3,0 174 | 58,1,1,120,284,0,0,160,0,1.8,1,0,2,0 175 | 58,1,2,132,224,0,0,173,0,3.2,2,2,3,0 176 | 60,1,0,130,206,0,0,132,1,2.4,1,2,3,0 177 | 40,1,0,110,167,0,0,114,1,2,1,0,3,0 178 | 60,1,0,117,230,1,1,160,1,1.4,2,2,3,0 179 | 64,1,2,140,335,0,1,158,0,0,2,0,2,0 180 | 43,1,0,120,177,0,0,120,1,2.5,1,0,3,0 181 | 57,1,0,150,276,0,0,112,1,0.6,1,1,1,0 182 | 55,1,0,132,353,0,1,132,1,1.2,1,1,3,0 183 | 65,0,0,150,225,0,0,114,0,1,1,3,3,0 184 | 61,0,0,130,330,0,0,169,0,0,2,0,2,0 185 | 58,1,2,112,230,0,0,165,0,2.5,1,1,3,0 186 | 50,1,0,150,243,0,0,128,0,2.6,1,0,3,0 187 | 44,1,0,112,290,0,0,153,0,0,2,1,2,0 188 | 60,1,0,130,253,0,1,144,1,1.4,2,1,3,0 189 | 54,1,0,124,266,0,0,109,1,2.2,1,1,3,0 190 | 50,1,2,140,233,0,1,163,0,0.6,1,1,3,0 191 | 41,1,0,110,172,0,0,158,0,0,2,0,3,0 192 | 51,0,0,130,305,0,1,142,1,1.2,1,0,3,0 193 | 58,1,0,128,216,0,0,131,1,2.2,1,3,3,0 194 | 54,1,0,120,188,0,1,113,0,1.4,1,1,3,0 195 | 60,1,0,145,282,0,0,142,1,2.8,1,2,3,0 196 | 60,1,2,140,185,0,0,155,0,3,1,0,2,0 197 | 59,1,0,170,326,0,0,140,1,3.4,0,0,3,0 198 | 46,1,2,150,231,0,1,147,0,3.6,1,0,2,0 199 | 67,1,0,125,254,1,1,163,0,0.2,1,2,3,0 200 | 62,1,0,120,267,0,1,99,1,1.8,1,2,3,0 201 | 65,1,0,110,248,0,0,158,0,0.6,2,2,1,0 202 | 44,1,0,110,197,0,0,177,0,0,2,1,2,0 203 | 60,1,0,125,258,0,0,141,1,2.8,1,1,3,0 204 | 58,1,0,150,270,0,0,111,1,0.8,2,0,3,0 205 | 68,1,2,180,274,1,0,150,1,1.6,1,0,3,0 206 | 62,0,0,160,164,0,0,145,0,6.2,0,3,3,0 207 | 52,1,0,128,255,0,1,161,1,0,2,1,3,0 208 | 59,1,0,110,239,0,0,142,1,1.2,1,1,3,0 209 | 60,0,0,150,258,0,0,157,0,2.6,1,2,3,0 210 | 49,1,2,120,188,0,1,139,0,2,1,3,3,0 211 | 59,1,0,140,177,0,1,162,1,0,2,1,3,0 212 | 57,1,2,128,229,0,0,150,0,0.4,1,1,3,0 213 | 61,1,0,120,260,0,1,140,1,3.6,1,1,3,0 214 | 39,1,0,118,219,0,1,140,0,1.2,1,0,3,0 215 | 61,0,0,145,307,0,0,146,1,1,1,0,3,0 216 | 56,1,0,125,249,1,0,144,1,1.2,1,1,2,0 217 | 43,0,0,132,341,1,0,136,1,3,1,0,3,0 218 | 62,0,2,130,263,0,1,97,0,1.2,1,1,3,0 219 | 63,1,0,130,330,1,0,132,1,1.8,2,3,3,0 220 | 65,1,0,135,254,0,0,127,0,2.8,1,1,3,0 221 | 48,1,0,130,256,1,0,150,1,0,2,2,3,0 222 | 63,0,0,150,407,0,0,154,0,4,1,3,3,0 223 | 55,1,0,140,217,0,1,111,1,5.6,0,0,3,0 224 | 65,1,3,138,282,1,0,174,0,1.4,1,1,2,0 225 | 56,0,0,200,288,1,0,133,1,4,0,2,3,0 226 | 54,1,0,110,239,0,1,126,1,2.8,1,1,3,0 227 | 70,1,0,145,174,0,1,125,1,2.6,0,0,3,0 228 | 62,1,1,120,281,0,0,103,0,1.4,1,1,3,0 229 | 35,1,0,120,198,0,1,130,1,1.6,1,0,3,0 230 | 59,1,3,170,288,0,0,159,0,0.2,1,0,3,0 231 | 64,1,2,125,309,0,1,131,1,1.8,1,0,3,0 232 | 47,1,2,108,243,0,1,152,0,0,2,0,2,0 233 | 57,1,0,165,289,1,0,124,0,1,1,3,3,0 234 | 55,1,0,160,289,0,0,145,1,0.8,1,1,3,0 235 | 64,1,0,120,246,0,0,96,1,2.2,0,1,2,0 236 | 70,1,0,130,322,0,0,109,0,2.4,1,3,2,0 237 | 51,1,0,140,299,0,1,173,1,1.6,2,0,3,0 238 | 58,1,0,125,300,0,0,171,0,0,2,2,3,0 239 | 60,1,0,140,293,0,0,170,0,1.2,1,2,3,0 240 | 77,1,0,125,304,0,0,162,1,0,2,3,2,0 241 | 35,1,0,126,282,0,0,156,1,0,2,0,3,0 242 | 70,1,2,160,269,0,1,112,1,2.9,1,1,3,0 243 | 59,0,0,174,249,0,1,143,1,0,1,0,2,0 244 | 64,1,0,145,212,0,0,132,0,2,1,2,1,0 245 | 57,1,0,152,274,0,1,88,1,1.2,1,1,3,0 246 | 56,1,0,132,184,0,0,105,1,2.1,1,1,1,0 247 | 48,1,0,124,274,0,0,166,0,0.5,1,0,3,0 248 | 56,0,0,134,409,0,0,150,1,1.9,1,2,3,0 249 | 66,1,1,160,246,0,1,120,1,0,1,3,1,0 250 | 54,1,1,192,283,0,0,195,0,0,2,1,3,0 251 | 69,1,2,140,254,0,0,146,0,2,1,3,3,0 252 | 51,1,0,140,298,0,1,122,1,4.2,1,3,3,0 253 | 43,1,0,132,247,1,0,143,1,0.1,1,4,3,0 254 | 62,0,0,138,294,1,1,106,0,1.9,1,3,2,0 255 | 67,1,0,100,299,0,0,125,1,0.9,1,2,2,0 256 | 59,1,3,160,273,0,0,125,0,0,2,0,2,0 257 | 45,1,0,142,309,0,0,147,1,0,1,3,3,0 258 | 58,1,0,128,259,0,0,130,1,3,1,2,3,0 259 | 50,1,0,144,200,0,0,126,1,0.9,1,0,3,0 260 | 62,0,0,150,244,0,1,154,1,1.4,1,0,2,0 261 | 38,1,3,120,231,0,1,182,1,3.8,1,0,3,0 262 | 66,0,0,178,228,1,1,165,1,1,1,2,3,0 263 | 52,1,0,112,230,0,1,160,0,0,2,1,2,0 264 | 53,1,0,123,282,0,1,95,1,2,1,2,3,0 265 | 63,0,0,108,269,0,1,169,1,1.8,1,2,2,0 266 | 54,1,0,110,206,0,0,108,1,0,1,1,2,0 267 | 66,1,0,112,212,0,0,132,1,0.1,2,1,2,0 268 | 55,0,0,180,327,0,2,117,1,3.4,1,0,2,0 269 | 49,1,2,118,149,0,0,126,0,0.8,2,3,2,0 270 | 54,1,0,122,286,0,0,116,1,3.2,1,2,2,0 271 | 56,1,0,130,283,1,0,103,1,1.6,0,0,3,0 272 | 46,1,0,120,249,0,0,144,0,0.8,2,0,3,0 273 | 61,1,3,134,234,0,1,145,0,2.6,1,2,2,0 274 | 67,1,0,120,237,0,1,71,0,1,1,0,2,0 275 | 58,1,0,100,234,0,1,156,0,0.1,2,1,3,0 276 | 47,1,0,110,275,0,0,118,1,1,1,1,2,0 277 | 52,1,0,125,212,0,1,168,0,1,2,2,3,0 278 | 58,1,0,146,218,0,1,105,0,2,1,1,3,0 279 | 57,1,1,124,261,0,1,141,0,0.3,2,0,3,0 280 | 58,0,1,136,319,1,0,152,0,0,2,2,2,0 281 | 61,1,0,138,166,0,0,125,1,3.6,1,1,2,0 282 | 42,1,0,136,315,0,1,125,1,1.8,1,0,1,0 283 | 52,1,0,128,204,1,1,156,1,1,1,0,0,0 284 | 59,1,2,126,218,1,1,134,0,2.2,1,1,1,0 285 | 40,1,0,152,223,0,1,181,0,0,2,0,3,0 286 | 61,1,0,140,207,0,0,138,1,1.9,2,1,3,0 287 | 46,1,0,140,311,0,1,120,1,1.8,1,2,3,0 288 | 59,1,3,134,204,0,1,162,0,0.8,2,2,2,0 289 | 57,1,1,154,232,0,0,164,0,0,2,1,2,0 290 | 57,1,0,110,335,0,1,143,1,3,1,1,3,0 291 | 55,0,0,128,205,0,2,130,1,2,1,1,3,0 292 | 61,1,0,148,203,0,1,161,0,0,2,1,3,0 293 | 58,1,0,114,318,0,2,140,0,4.4,0,3,1,0 294 | 58,0,0,170,225,1,0,146,1,2.8,1,2,1,0 295 | 67,1,2,152,212,0,0,150,0,0.8,1,0,3,0 296 | 44,1,0,120,169,0,1,144,1,2.8,0,0,1,0 297 | 63,1,0,140,187,0,0,144,1,4,2,2,3,0 298 | 63,0,0,124,197,0,1,136,1,0,1,0,2,0 299 | 59,1,0,164,176,1,0,90,0,1,1,2,1,0 300 | 57,0,0,140,241,0,1,123,1,0.2,1,0,3,0 301 | 45,1,3,110,264,0,1,132,0,1.2,1,0,3,0 302 | 68,1,0,144,193,1,1,141,0,3.4,1,2,3,0 303 | 57,1,0,130,131,0,1,115,1,1.2,1,1,3,0 304 | 57,0,1,130,236,0,0,174,0,0,1,1,2,0 305 | -------------------------------------------------------------------------------- /uci_heart_disease/Heart Disease Inference.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## Heart Disease Inference\n", 8 | "\n", 9 | "In this notebook, we will try to look at just the inference part of the heart disease classification solution\n", 10 | "\n", 11 | "The process of applying the same transformations like data pre-processing, feature engineering etc. which was applied during the training process, and then applying the trained ML model to generate predictions is termed as the inference process." 12 | ] 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "### Import Modules" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 1, 24 | "metadata": {}, 25 | "outputs": [], 26 | "source": [ 27 | "import pandas as pd\n", 28 | "import numpy as np" 29 | ] 30 | }, 31 | { 32 | "cell_type": "markdown", 33 | "metadata": {}, 34 | "source": [ 35 | "### Get Inference Data" 36 | ] 37 | }, 38 | { 39 | "cell_type": "code", 40 | "execution_count": 2, 41 | "metadata": {}, 42 | "outputs": [], 43 | "source": [ 44 | "# in real-time use cases, this code should be replaced with live flowing data\n", 45 | "\n", 46 | "data = pd.read_csv(\"Data/inference_heart_disease.csv\") # Live connection to the database\n", 47 | "data.drop_duplicates(subset=None, inplace=True)\n", 48 | "data.duplicated().any()\n", 49 | "inference_df = data.copy()\n", 50 | "inference_data, labels = inference_df[inference_df.columns.drop('target')], inference_df['target']" 51 | ] 52 | }, 53 | { 54 | "cell_type": "code", 55 | "execution_count": 3, 56 | "metadata": {}, 57 | "outputs": [ 58 | { 59 | "data": { 60 | "text/plain": [ 61 | "Index(['age', 'sex', 'chest_pain_type', 'resting_bp', 'cholestoral',\n", 62 | " 'fasting_blood_sugar', 'restecg', 'max_hr', 'exang', 'oldpeak', 'slope',\n", 63 | " 'num_major_vessels', 'thal'],\n", 64 | " dtype='object')" 65 | ] 66 | }, 67 | "execution_count": 3, 68 | "metadata": {}, 69 | "output_type": "execute_result" 70 | } 71 | ], 72 | "source": [ 73 | "inference_data.columns" 74 | ] 75 | }, 76 | { 77 | "cell_type": "code", 78 | "execution_count": 4, 79 | "metadata": {}, 80 | "outputs": [ 81 | { 82 | "data": { 83 | "text/html": [ 84 | "
\n", 85 | "\n", 98 | "\n", 99 | " \n", 100 | " \n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | " \n", 119 | " \n", 120 | " \n", 121 | " \n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | " \n", 159 | " \n", 160 | " \n", 161 | " \n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | " \n", 166 | " \n", 167 | " \n", 168 | " \n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | "
agesexchest_pain_typeresting_bpcholestoralfasting_blood_sugarrestecgmax_hrexangoldpeakslopenum_major_vesselsthal
066101203020015100.4102
152101122300116000.0212
263011401950117900.0222
346121502310114703.6102
463101302540014701.4113
\n", 200 | "
" 201 | ], 202 | "text/plain": [ 203 | " age sex chest_pain_type resting_bp cholestoral fasting_blood_sugar \\\n", 204 | "0 66 1 0 120 302 0 \n", 205 | "1 52 1 0 112 230 0 \n", 206 | "2 63 0 1 140 195 0 \n", 207 | "3 46 1 2 150 231 0 \n", 208 | "4 63 1 0 130 254 0 \n", 209 | "\n", 210 | " restecg max_hr exang oldpeak slope num_major_vessels thal \n", 211 | "0 0 151 0 0.4 1 0 2 \n", 212 | "1 1 160 0 0.0 2 1 2 \n", 213 | "2 1 179 0 0.0 2 2 2 \n", 214 | "3 1 147 0 3.6 1 0 2 \n", 215 | "4 0 147 0 1.4 1 1 3 " 216 | ] 217 | }, 218 | "execution_count": 4, 219 | "metadata": {}, 220 | "output_type": "execute_result" 221 | } 222 | ], 223 | "source": [ 224 | "inference_data.head()" 225 | ] 226 | }, 227 | { 228 | "cell_type": "markdown", 229 | "metadata": {}, 230 | "source": [ 231 | "### Apply Same Pre-processing" 232 | ] 233 | }, 234 | { 235 | "cell_type": "code", 236 | "execution_count": 5, 237 | "metadata": {}, 238 | "outputs": [ 239 | { 240 | "data": { 241 | "text/html": [ 242 | "
\n", 243 | "\n", 256 | "\n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | " \n", 267 | " \n", 268 | " \n", 269 | " \n", 270 | " \n", 271 | " \n", 272 | " \n", 273 | " \n", 274 | " \n", 275 | " \n", 276 | " \n", 277 | " \n", 278 | " \n", 279 | " \n", 280 | " \n", 281 | " \n", 282 | " \n", 283 | " \n", 284 | " \n", 285 | " \n", 286 | " \n", 287 | " \n", 288 | " \n", 289 | " \n", 290 | " \n", 291 | " \n", 292 | " \n", 293 | " \n", 294 | " \n", 295 | " \n", 296 | " \n", 297 | " \n", 298 | " \n", 299 | " \n", 300 | " \n", 301 | " \n", 302 | " \n", 303 | " \n", 304 | " \n", 305 | " \n", 306 | " \n", 307 | " \n", 308 | " \n", 309 | " \n", 310 | " \n", 311 | " \n", 312 | " \n", 313 | " \n", 314 | " \n", 315 | " \n", 316 | " \n", 317 | " \n", 318 | " \n", 319 | " \n", 320 | " \n", 321 | " \n", 322 | " \n", 323 | " \n", 324 | " \n", 325 | " \n", 326 | " \n", 327 | " \n", 328 | " \n", 329 | " \n", 330 | " \n", 331 | " \n", 332 | " \n", 333 | " \n", 334 | " \n", 335 | " \n", 336 | " \n", 337 | " \n", 338 | " \n", 339 | " \n", 340 | " \n", 341 | " \n", 342 | " \n", 343 | " \n", 344 | " \n", 345 | " \n", 346 | " \n", 347 | " \n", 348 | " \n", 349 | " \n", 350 | " \n", 351 | " \n", 352 | " \n", 353 | " \n", 354 | " \n", 355 | " \n", 356 | " \n", 357 | " \n", 358 | " \n", 359 | " \n", 360 | " \n", 361 | " \n", 362 | " \n", 363 | " \n", 364 | " \n", 365 | " \n", 366 | " \n", 367 | " \n", 368 | " \n", 369 | " \n", 370 | " \n", 371 | " \n", 372 | " \n", 373 | " \n", 374 | " \n", 375 | " \n", 376 | " \n", 377 | " \n", 378 | " \n", 379 | " \n", 380 | " \n", 381 | " \n", 382 | " \n", 383 | " \n", 384 | " \n", 385 | " \n", 386 | " \n", 387 | " \n", 388 | " \n", 389 | " \n", 390 | " \n", 391 | " \n", 392 | " \n", 393 | " \n", 394 | " \n", 395 | " \n", 396 | " \n", 397 | " \n", 398 | " \n", 399 | " \n", 400 | " \n", 401 | " \n", 402 | " \n", 403 | " \n", 404 | " \n", 405 | " \n", 406 | " \n", 407 | " \n", 408 | " \n", 409 | " \n", 410 | " \n", 411 | " \n", 412 | " \n", 413 | " \n", 414 | " \n", 415 | " \n", 416 | " \n", 417 | " \n", 418 | " \n", 419 | " \n", 420 | " \n", 421 | " \n", 422 | " \n", 423 | " \n", 424 | " \n", 425 | " \n", 426 | " \n", 427 | " \n", 428 | " \n", 429 | " \n", 430 | " \n", 431 | " \n", 432 | " \n", 433 | " \n", 434 | " \n", 435 | " \n", 436 | " \n", 437 | " \n", 438 | " \n", 439 | " \n", 440 | " \n", 441 | " \n", 442 | " \n", 443 | " \n", 444 | " \n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | " \n", 467 | " \n", 468 | " \n", 469 | " \n", 470 | " \n", 471 | " \n", 472 | " \n", 473 | " \n", 474 | " \n", 475 | " \n", 476 | " \n", 477 | " \n", 478 | " \n", 479 | " \n", 480 | " \n", 481 | " \n", 482 | " \n", 483 | " \n", 484 | " \n", 485 | " \n", 486 | " \n", 487 | " \n", 488 | " \n", 489 | " \n", 490 | " \n", 491 | " \n", 492 | " \n", 493 | " \n", 494 | " \n", 495 | " \n", 496 | " \n", 497 | " \n", 498 | " \n", 499 | " \n", 500 | " \n", 501 | " \n", 502 | " \n", 503 | " \n", 504 | " \n", 505 | " \n", 506 | " \n", 507 | " \n", 508 | " \n", 509 | " \n", 510 | " \n", 511 | " \n", 512 | " \n", 513 | " \n", 514 | " \n", 515 | " \n", 516 | " \n", 517 | " \n", 518 | " \n", 519 | " \n", 520 | " \n", 521 | " \n", 522 | " \n", 523 | " \n", 524 | " \n", 525 | " \n", 526 | " \n", 527 | " \n", 528 | " \n", 529 | " \n", 530 | " \n", 531 | " \n", 532 | " \n", 533 | " \n", 534 | " \n", 535 | " \n", 536 | " \n", 537 | " \n", 538 | " \n", 539 | " \n", 540 | " \n", 541 | " \n", 542 | " \n", 543 | " \n", 544 | " \n", 545 | " \n", 546 | " \n", 547 | " \n", 548 | " \n", 549 | " \n", 550 | " \n", 551 | " \n", 552 | " \n", 553 | " \n", 554 | " \n", 555 | " \n", 556 | " \n", 557 | " \n", 558 | " \n", 559 | " \n", 560 | " \n", 561 | " \n", 562 | " \n", 563 | " \n", 564 | " \n", 565 | " \n", 566 | " \n", 567 | " \n", 568 | " \n", 569 | " \n", 570 | " \n", 571 | " \n", 572 | " \n", 573 | " \n", 574 | " \n", 575 | " \n", 576 | " \n", 577 | " \n", 578 | " \n", 579 | " \n", 580 | " \n", 581 | " \n", 582 | " \n", 583 | " \n", 584 | " \n", 585 | " \n", 586 | " \n", 587 | " \n", 588 | " \n", 589 | " \n", 590 | " \n", 591 | " \n", 592 | " \n", 593 | " \n", 594 | " \n", 595 | " \n", 596 | " \n", 597 | " \n", 598 | " \n", 599 | " \n", 600 | " \n", 601 | " \n", 602 | " \n", 603 | " \n", 604 | " \n", 605 | " \n", 606 | " \n", 607 | " \n", 608 | " \n", 609 | " \n", 610 | " \n", 611 | " \n", 612 | " \n", 613 | " \n", 614 | " \n", 615 | " \n", 616 | " \n", 617 | " \n", 618 | " \n", 619 | " \n", 620 | " \n", 621 | " \n", 622 | " \n", 623 | " \n", 624 | " \n", 625 | " \n", 626 | " \n", 627 | " \n", 628 | " \n", 629 | " \n", 630 | " \n", 631 | " \n", 632 | " \n", 633 | " \n", 634 | " \n", 635 | " \n", 636 | " \n", 637 | " \n", 638 | " \n", 639 | " \n", 640 | " \n", 641 | " \n", 642 | " \n", 643 | " \n", 644 | " \n", 645 | " \n", 646 | " \n", 647 | " \n", 648 | " \n", 649 | " \n", 650 | " \n", 651 | " \n", 652 | " \n", 653 | " \n", 654 | " \n", 655 | " \n", 656 | " \n", 657 | " \n", 658 | " \n", 659 | " \n", 660 | " \n", 661 | " \n", 662 | " \n", 663 | " \n", 664 | " \n", 665 | " \n", 666 | " \n", 667 | " \n", 668 | " \n", 669 | " \n", 670 | " \n", 671 | " \n", 672 | " \n", 673 | " \n", 674 | " \n", 675 | " \n", 676 | " \n", 677 | " \n", 678 | " \n", 679 | " \n", 680 | " \n", 681 | " \n", 682 | " \n", 683 | " \n", 684 | " \n", 685 | " \n", 686 | " \n", 687 | " \n", 688 | " \n", 689 | " \n", 690 | " \n", 691 | " \n", 692 | " \n", 693 | " \n", 694 | " \n", 695 | " \n", 696 | " \n", 697 | " \n", 698 | " \n", 699 | " \n", 700 | " \n", 701 | " \n", 702 | " \n", 703 | " \n", 704 | " \n", 705 | " \n", 706 | " \n", 707 | " \n", 708 | " \n", 709 | " \n", 710 | " \n", 711 | " \n", 712 | " \n", 713 | " \n", 714 | " \n", 715 | " \n", 716 | " \n", 717 | " \n", 718 | " \n", 719 | " \n", 720 | " \n", 721 | " \n", 722 | " \n", 723 | " \n", 724 | " \n", 725 | " \n", 726 | " \n", 727 | " \n", 728 | " \n", 729 | " \n", 730 | " \n", 731 | " \n", 732 | " \n", 733 | " \n", 734 | " \n", 735 | " \n", 736 | " \n", 737 | " \n", 738 | " \n", 739 | " \n", 740 | " \n", 741 | " \n", 742 | " \n", 743 | " \n", 744 | " \n", 745 | " \n", 746 | " \n", 747 | " \n", 748 | " \n", 749 | " \n", 750 | " \n", 751 | " \n", 752 | " \n", 753 | " \n", 754 | " \n", 755 | " \n", 756 | " \n", 757 | " \n", 758 | " \n", 759 | " \n", 760 | " \n", 761 | " \n", 762 | " \n", 763 | " \n", 764 | " \n", 765 | "
0123456789...13141516171819202122
01.0000001.00.4642860.8146070.00.4574470.00.1111110.00.0...0.01.00.01.00.00.00.01.00.00.0
10.6216221.00.3214290.4101120.00.5531910.00.0000000.50.0...0.00.01.01.00.00.00.00.01.00.0
20.9189190.00.8214290.2134830.00.7553190.00.0000001.00.0...0.00.01.00.01.00.00.00.01.00.0
30.4594591.01.0000000.4157300.00.4148940.01.0000000.00.0...0.01.00.00.00.01.00.00.01.00.0
40.9189191.00.6428570.5449440.00.4148940.00.3888890.50.0...0.01.00.01.00.00.00.01.00.00.0
50.3243241.00.6428570.3202250.00.6382980.00.5555560.00.0...0.01.00.00.00.01.00.01.00.00.0
60.2702700.00.0000000.2359550.00.7553190.00.0000000.00.0...0.00.01.00.00.01.00.00.01.00.0
70.5135141.00.6428570.5561801.00.4468091.00.0000001.00.0...0.00.01.01.00.00.00.01.00.00.0
80.7567571.00.2857141.0000000.00.3723401.00.8333330.50.0...0.01.00.01.00.00.00.00.01.00.0
90.4864861.00.7857140.5617980.00.5106380.00.0000000.00.0...0.00.01.00.00.01.00.01.00.00.0
100.7297301.00.5535710.5168541.00.3829791.00.3333330.50.0...0.01.00.01.00.00.00.01.00.00.0
110.7567570.00.8214290.4719100.00.1595741.00.0555560.00.0...0.01.00.01.00.00.00.00.01.00.0
120.6486491.00.8571430.3876400.00.0319151.00.0000000.00.0...0.00.01.01.00.00.00.01.00.00.0
130.3243241.00.4642860.0000000.00.7872340.00.0000000.00.0...0.00.01.00.01.00.00.00.01.00.0
140.6756761.00.2857140.2752810.00.0000001.00.0000000.50.0...0.01.00.01.00.00.00.01.00.00.0
150.7027030.00.7321430.5224720.00.5638300.00.3888890.00.0...0.01.00.00.01.00.00.01.00.00.0
160.3513511.00.8214290.3876400.00.7446810.00.0000000.00.0...0.00.01.01.00.00.00.00.01.00.0
170.0000001.00.6428570.2640450.01.0000000.00.0000000.00.0...0.00.01.00.01.00.00.01.00.00.0
180.5675680.00.4642860.3483150.00.5319150.00.4444440.00.0...0.01.00.00.00.01.00.00.01.00.0
190.6486491.00.8214290.2584271.00.5000001.00.8611110.00.0...1.00.00.01.00.00.00.01.00.00.0
\n", 766 | "

20 rows × 23 columns

\n", 767 | "
" 768 | ], 769 | "text/plain": [ 770 | " 0 1 2 3 4 5 6 7 8 9 \\\n", 771 | "0 1.000000 1.0 0.464286 0.814607 0.0 0.457447 0.0 0.111111 0.0 0.0 \n", 772 | "1 0.621622 1.0 0.321429 0.410112 0.0 0.553191 0.0 0.000000 0.5 0.0 \n", 773 | "2 0.918919 0.0 0.821429 0.213483 0.0 0.755319 0.0 0.000000 1.0 0.0 \n", 774 | "3 0.459459 1.0 1.000000 0.415730 0.0 0.414894 0.0 1.000000 0.0 0.0 \n", 775 | "4 0.918919 1.0 0.642857 0.544944 0.0 0.414894 0.0 0.388889 0.5 0.0 \n", 776 | "5 0.324324 1.0 0.642857 0.320225 0.0 0.638298 0.0 0.555556 0.0 0.0 \n", 777 | "6 0.270270 0.0 0.000000 0.235955 0.0 0.755319 0.0 0.000000 0.0 0.0 \n", 778 | "7 0.513514 1.0 0.642857 0.556180 1.0 0.446809 1.0 0.000000 1.0 0.0 \n", 779 | "8 0.756757 1.0 0.285714 1.000000 0.0 0.372340 1.0 0.833333 0.5 0.0 \n", 780 | "9 0.486486 1.0 0.785714 0.561798 0.0 0.510638 0.0 0.000000 0.0 0.0 \n", 781 | "10 0.729730 1.0 0.553571 0.516854 1.0 0.382979 1.0 0.333333 0.5 0.0 \n", 782 | "11 0.756757 0.0 0.821429 0.471910 0.0 0.159574 1.0 0.055556 0.0 0.0 \n", 783 | "12 0.648649 1.0 0.857143 0.387640 0.0 0.031915 1.0 0.000000 0.0 0.0 \n", 784 | "13 0.324324 1.0 0.464286 0.000000 0.0 0.787234 0.0 0.000000 0.0 0.0 \n", 785 | "14 0.675676 1.0 0.285714 0.275281 0.0 0.000000 1.0 0.000000 0.5 0.0 \n", 786 | "15 0.702703 0.0 0.732143 0.522472 0.0 0.563830 0.0 0.388889 0.0 0.0 \n", 787 | "16 0.351351 1.0 0.821429 0.387640 0.0 0.744681 0.0 0.000000 0.0 0.0 \n", 788 | "17 0.000000 1.0 0.642857 0.264045 0.0 1.000000 0.0 0.000000 0.0 0.0 \n", 789 | "18 0.567568 0.0 0.464286 0.348315 0.0 0.531915 0.0 0.444444 0.0 0.0 \n", 790 | "19 0.648649 1.0 0.821429 0.258427 1.0 0.500000 1.0 0.861111 0.0 0.0 \n", 791 | "\n", 792 | " ... 13 14 15 16 17 18 19 20 21 22 \n", 793 | "0 ... 0.0 1.0 0.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 \n", 794 | "1 ... 0.0 0.0 1.0 1.0 0.0 0.0 0.0 0.0 1.0 0.0 \n", 795 | "2 ... 0.0 0.0 1.0 0.0 1.0 0.0 0.0 0.0 1.0 0.0 \n", 796 | "3 ... 0.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 1.0 0.0 \n", 797 | "4 ... 0.0 1.0 0.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 \n", 798 | "5 ... 0.0 1.0 0.0 0.0 0.0 1.0 0.0 1.0 0.0 0.0 \n", 799 | "6 ... 0.0 0.0 1.0 0.0 0.0 1.0 0.0 0.0 1.0 0.0 \n", 800 | "7 ... 0.0 0.0 1.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 \n", 801 | "8 ... 0.0 1.0 0.0 1.0 0.0 0.0 0.0 0.0 1.0 0.0 \n", 802 | "9 ... 0.0 0.0 1.0 0.0 0.0 1.0 0.0 1.0 0.0 0.0 \n", 803 | "10 ... 0.0 1.0 0.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 \n", 804 | "11 ... 0.0 1.0 0.0 1.0 0.0 0.0 0.0 0.0 1.0 0.0 \n", 805 | "12 ... 0.0 0.0 1.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 \n", 806 | "13 ... 0.0 0.0 1.0 0.0 1.0 0.0 0.0 0.0 1.0 0.0 \n", 807 | "14 ... 0.0 1.0 0.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 \n", 808 | "15 ... 0.0 1.0 0.0 0.0 1.0 0.0 0.0 1.0 0.0 0.0 \n", 809 | "16 ... 0.0 0.0 1.0 1.0 0.0 0.0 0.0 0.0 1.0 0.0 \n", 810 | "17 ... 0.0 0.0 1.0 0.0 1.0 0.0 0.0 1.0 0.0 0.0 \n", 811 | "18 ... 0.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 1.0 0.0 \n", 812 | "19 ... 1.0 0.0 0.0 1.0 0.0 0.0 0.0 1.0 0.0 0.0 \n", 813 | "\n", 814 | "[20 rows x 23 columns]" 815 | ] 816 | }, 817 | "execution_count": 5, 818 | "metadata": {}, 819 | "output_type": "execute_result" 820 | } 821 | ], 822 | "source": [ 823 | "features_to_encode = ['thal', 'slope', 'chest_pain_type', 'restecg']\n", 824 | "encoded_df = pd.DataFrame(columns= ['age', 'sex', 'resting_bp', 'cholestoral', 'fasting_blood_sugar',\n", 825 | " 'max_hr', 'exang', 'oldpeak', 'num_major_vessels', 'thal_0', 'thal_1',\n", 826 | " 'thal_2', 'thal_3', 'slope_0', 'slope_1', 'slope_2',\n", 827 | " 'chest_pain_type_0', 'chest_pain_type_1', 'chest_pain_type_2',\n", 828 | " 'chest_pain_type_3', 'restecg_0', 'restecg_1', 'restecg_2'])\n", 829 | "placeholder_df = pd.DataFrame()\n", 830 | "\n", 831 | "# One-Hot Encoding using get_dummies for the specified categorical features\n", 832 | "for f in features_to_encode:\n", 833 | " if(f in inference_data.columns):\n", 834 | " encoded = pd.get_dummies(inference_data[f])\n", 835 | " encoded = encoded.add_prefix(f + '_')\n", 836 | " placeholder_df = pd.concat([placeholder_df, encoded], axis=1)\n", 837 | " else:\n", 838 | " print('Feature not found')\n", 839 | "\n", 840 | "# Implement these steps to prevent dimension mismatch during inference\n", 841 | "for feature in encoded_df.columns:\n", 842 | " if feature in inference_data.columns:\n", 843 | " encoded_df[feature] = inference_data[feature]\n", 844 | " if feature in placeholder_df.columns:\n", 845 | " encoded_df[feature] = placeholder_df[feature]\n", 846 | "# fill all null values\n", 847 | "encoded_df.fillna(0, inplace=True)\n", 848 | "\n", 849 | "from sklearn import preprocessing\n", 850 | "# normalization\n", 851 | "val = encoded_df.values \n", 852 | "min_max_normalizer = preprocessing.MinMaxScaler()\n", 853 | "norm_val = min_max_normalizer.fit_transform(val)\n", 854 | "df2 = pd.DataFrame(norm_val)\n", 855 | "\n", 856 | "processed_inference_data = df2.copy()\n", 857 | "processed_inference_data" 858 | ] 859 | }, 860 | { 861 | "cell_type": "markdown", 862 | "metadata": {}, 863 | "source": [ 864 | "### Load Saved Model" 865 | ] 866 | }, 867 | { 868 | "cell_type": "code", 869 | "execution_count": null, 870 | "metadata": {}, 871 | "outputs": [], 872 | "source": [ 873 | "import joblib\n", 874 | "model = joblib.load('aditya_model1_adaboost.joblib')\n", 875 | "model" 876 | ] 877 | }, 878 | { 879 | "cell_type": "markdown", 880 | "metadata": {}, 881 | "source": [ 882 | "### Prediction on inference data" 883 | ] 884 | }, 885 | { 886 | "cell_type": "code", 887 | "execution_count": 7, 888 | "metadata": {}, 889 | "outputs": [ 890 | { 891 | "data": { 892 | "text/plain": [ 893 | "array([1., 1., 1., 1., 0., 1., 1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1.,\n", 894 | " 1., 1., 0.])" 895 | ] 896 | }, 897 | "execution_count": 7, 898 | "metadata": {}, 899 | "output_type": "execute_result" 900 | } 901 | ], 902 | "source": [ 903 | "model.predict(processed_inference_data)" 904 | ] 905 | }, 906 | { 907 | "cell_type": "markdown", 908 | "metadata": {}, 909 | "source": [ 910 | "### Scoring check on prediction" 911 | ] 912 | }, 913 | { 914 | "cell_type": "code", 915 | "execution_count": 8, 916 | "metadata": {}, 917 | "outputs": [ 918 | { 919 | "data": { 920 | "text/plain": [ 921 | "0.85" 922 | ] 923 | }, 924 | "execution_count": 8, 925 | "metadata": {}, 926 | "output_type": "execute_result" 927 | } 928 | ], 929 | "source": [ 930 | "from sklearn.metrics import accuracy_score\n", 931 | "accuracy_score(labels, model.predict(processed_inference_data))" 932 | ] 933 | }, 934 | { 935 | "cell_type": "code", 936 | "execution_count": null, 937 | "metadata": {}, 938 | "outputs": [], 939 | "source": [] 940 | } 941 | ], 942 | "metadata": { 943 | "kernelspec": { 944 | "display_name": "Python 3", 945 | "language": "python", 946 | "name": "python3" 947 | }, 948 | "language_info": { 949 | "codemirror_mode": { 950 | "name": "ipython", 951 | "version": 3 952 | }, 953 | "file_extension": ".py", 954 | "mimetype": "text/x-python", 955 | "name": "python", 956 | "nbconvert_exporter": "python", 957 | "pygments_lexer": "ipython3", 958 | "version": "3.7.7" 959 | } 960 | }, 961 | "nbformat": 4, 962 | "nbformat_minor": 5 963 | } 964 | --------------------------------------------------------------------------------