MachineLearing-Classification

Dataset: The Wisconsin Cancer Dataset

https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/

Model type : <DecisionTree_entropy, DecisionTree_gini, LogisticRegression, SVM>

-Various data scaling methods and encoding methods
-Various values of the model parameters for each model
-Various values for the hyperparameters
-Various numbers 𝑘for 𝑘 fold cross validation

You can use AutoML function to automatically run different combinations of the above within a
“single major function”.

def AutoML(scaler, encoder, model, label, target) :

if not isinstance(train, pd.DataFrame):
    raise TypeError
# if not isinstance(scaler, dict):
#     raise TypeError

predicted = {}

print("Encoder Type : ",encoder)
print("Scaler Type : ",scaler)
print("Model Type : ",model)

hyper_param = {
"k-means": [5],
"em": [5],
"clarans": {"numCluster":[4], "numLocal":[5], "maxNeighbor":[5]},
"dbscan": {"eps":[0.1], "minSample":[4]}

for e in encoder:
    e_train = Encoding(train, e)
    print("------------------------------------")
    print("Encoder Type: ",e)
    for s in scaler:
        print("------------------------------------")
        print("Scaler Type : " , s)
        s_train = Scaling(e_train,s)
        for m in model:
            print("------------------------------------")
            print("Model Type : ",m)
            predicted = predict(m, label, target)

AutoML(scaler, encoder, model, df_label, df_target)

Result :