Scikit-learn Classification

Machine Learning with scikit-learn

Before using supervise learning

• Requirements
  • No missing values
  • Data in numeriv format
  • Data sorted in pandas DataFrame or NumPy array
• Perform Exploratory Data Analysis (EDA) first

Scikit-learn Syntax

1. Import scikit-learn.

    from sklearn.module import Model
   

   K-Nearest-Neighbors:

    from sklearn.neighbors import KNeighborsClassifier
   

2. Train/test split.

    from sklearn.model_selection import train_test_split
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 21 stratify = y)
   

3. Build a model.

      model = Model()
   

   K-Nearest-Neighbors:

    knn = KneighborsClassifier(n_neighbors=15)
   

4. Model learns from the labeled data (training data) passed to it.

    model.fit(X,y)
   

   K-Nearest-Neighbors:

      knn.fit(X,y)
   

5. Pass unlabeled data to the model as input, model predicts the labels of the unseen data.

      prediction = model.predict(X_new)
   

   Check accuracy K-Nearest-Neighbors:

      knn.score(X_test,y_test))
   

References

• Supervised Learning with Scikit-Learn on DataCamp