You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
46 lines
1.6 KiB
46 lines
1.6 KiB
from sklearn.linear_model import LogisticRegression
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.metrics import accuracy_score
|
|
from sklearn.preprocessing import LabelEncoder
|
|
|
|
def perform_classification(data, data_name, target_name, test_size):
|
|
X = data[data_name]
|
|
y = data[target_name]
|
|
|
|
label_encoders = {}
|
|
for column in X.select_dtypes(include=['object']).columns:
|
|
le = LabelEncoder()
|
|
X[column] = le.fit_transform(X[column])
|
|
label_encoders[column] = le
|
|
|
|
if y.dtype == 'object':
|
|
le = LabelEncoder()
|
|
y = le.fit_transform(y)
|
|
label_encoders[target_name] = le
|
|
else:
|
|
if y.nunique() > 10:
|
|
raise ValueError("The target variable seems to be continuous. Please select a categorical target for classification.")
|
|
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=42)
|
|
|
|
model = LogisticRegression()
|
|
model.fit(X_train, y_train)
|
|
y_pred = model.predict(X_test)
|
|
accuracy = accuracy_score(y_test, y_pred)
|
|
|
|
return model, label_encoders, accuracy
|
|
|
|
def make_prediction(model, label_encoders, data_name, target_name, input_values):
|
|
X_new = []
|
|
for feature, value in zip(data_name, input_values):
|
|
if feature in label_encoders:
|
|
value = label_encoders[feature].transform([value])[0]
|
|
X_new.append(value)
|
|
|
|
prediction = model.predict([X_new])
|
|
|
|
if target_name in label_encoders:
|
|
prediction = label_encoders[target_name].inverse_transform(prediction)
|
|
|
|
return prediction[0]
|