PYTHON FOR DATA                                                                                                                                      Working On Model
                                     SCIENCE                                                                                                       Model Choosing                                                                                  T r a i n - T e s t  
                                                                                                                                                                                                                                                           Data
                           CHEAT SHEET                                                                       Supervised Learning Estimator:           •   Naive Bayes:                           Unsupervised Learning Estimator:
                                                                                                             • Linear Regression:                     >>> from sklearn.naive_bayesimport         •   Principal Component Analysis (PCA):     Supervised:
                                                                                                             >>>from sklearn.linear_modelimport       GaussianNB                                 >>> from sklearn.decomposition import       >>>new_ lr.fit(X, y)
                                                                                                             LinearRegression                         >>> new_gnb= GaussianNB()                  PCA                                         >>> knn.fit(X_train, y_train)
                    Python Scikit-Learn                                                                      >>> new_lr =                             •   KNN:                                   >>> new_pca= PCA(n_components=0.95)         >>>new_svc.fit(X_train, y_train)
                                                                                                             LinearRegression(normalize=True)         >>> from sklearnimport neighbors           •   K Means:                                Unsupervised : 
                                                                                                             • Support Vector Machine:                >>>                                        >>>from sklearn.cluster import KMeans       >>> k_means.fit(X_train)
                                                                                                             >>> from sklearn.svmimport SVC           knn=neighbors.KNeighborsClassifier(n_ne    >>> k_means= KMeans(n_clusters=5,           >>> pca_model_fit= 
                                                                                                             >>> new_svc= SVC(kernel='linear')        ighbors=1)                                 random_state=0)                             new_pca.fit_transform(X_train)
                                  I n t r o d u c t i o n
        Scikit-learn:“sklearn" is a machine learning library for the Python programming language. 
        Simple and efficient tool for data mining, Data analysis and Machine Learning.                                                                                   P o s t - P r o c e s s i n g
                                 Importing Convention -import sklearn
                                P r e p r o c e s s i n g                                                           P r e d i c t i o n                                                                  Model Tuning
                                                                                                             Supervised:                                          Grid Search:                                             Randomized Parameter Optimization:
            Data Loading                                       T r a i n - T e s t                           >>>y_predict=                                        >>> from sklearn.grid_searchimport GridSearchCV          >>> from sklearn.grid_searchimport RandomizedSearchCV
                                                                                                             new_svc.predict(np.random.random((3,5)))             >>> params= {"n_neighbors": np.arange(1,3), "metric":    >>> params= {"n_neighbors": range(1,5), "weights": 
        • Using NumPy:                                                 Data                                  >>>y_predict= new_lr.predict(X_test)                           ["euclidean", "cityblock"]}                    ["uniform", "distance"]}
        >>>import numpyas np                                                                                 >>>y_predict= knn.predict_proba(X_test)              >>> grid = GridSearchCV(estimator=knn,                   >>> rsearch = RandomizedSearchCV(estimator=knn, 
        >>>a=np.array([(1,2,3,4),(7,8,9,10)],dtype=int)                                                                                                           param_grid=params)                                       param_distributions=params, cv=4, n_iter=8, random_state=5)
        >>>data = np.loadtxt('file_name.csv',               >>>from sklearn.model_selection                  Unsupervised:                                        >>> grid.fit(X_train, y_train)                           >>> rsearch.fit(X_train, y_train)
           delimiter=',')                                   import train_test_split                          >>>y_pred= k_means.predict(X_test)                   >>> print(grid.best_score_)                              >>> print(rsearch.best_score_)
                                                                                                                                                                  >>> print(grid.best_estimator_.n_neighbors)
        • Using Pandas: 
        >>>import pandas as pd                              >>> X_train, X_test, y_train, y_test = 
        >>>df=pd.read_csvȋǮfile_name.csvǯ,header=0)         train_test_split(X,y,random_state=0)                                                                  E v a l u a t e   P e r f o r m a n c e
                                                                                                              Classification:                       Regression:                                                Clustering:                                Cross-validation:
                             Data Preparation                                                                 1. Confusion Matrix:                  1. Mean Absolute Error:                                    1. Homogeneity:                            >>> from 
                                                                                                              >>> from sklearn.metricsimport        >>> from sklearn.metricsimport mean_absolute_error         >>> from sklearn.metricsimport             sklearn.cross_validation
                                                                                                                    confusion_matrix                                                                           homogeneity_score                          import cross_val_score
         • Standardization                               • Normalization                                      >>> print(confusion_matrix(y_test,    >>> y_true= [3, -0.5, 2]                                   >>> homogeneity_score(y_true,              >>> 
         >>>from sklearn.preprocessing import            >>>from sklearn.preprocessing import                       y_pred))                        >>> mean_absolute_error(y_true, y_predict)                 y_predict)                                 print(cross_val_score(knn, 
         StandardScaler                                    Normalizer                                         2. Accuracy Score:                    2. Mean Squared Error:                                     2. V-measure:                              X_train, y_train, cv=4))
         >>>get_names= df.columns                        >>>pd.read_csv("File_name.csv")                      >>> knn.score(X_test, y_test)         >>> from sklearn.metricsimport mean_squared_error          >>> from sklearn.metricsimport             >>> 
         >>>scaler =                                     >>>x_array= np.array(df[ǮColumn1ǯ]Ȍ                  >>> from sklearn.metricsimport        >>> mean_squared_error(y_test, y_predict)                  v_measure_score                            print(cross_val_score(new_
         preprocessing.StandardScaler()                  #Normalize   Column1                                       accuracy_score                  3. R² Score :                                              >>> metrics.v_measure_score(y_true,        lr, X, y, cv=2))
         >>>scaled_df= scaler.fit_transform(df)          >>>normalized_X=                                     >>> accuracy_score(y_test, y_pred)    >>> from sklearn.metricsimport r2_score                    y_predict)
         >>>scaled_df=                                   preprocessing.normalize([x_array])                                                         >>> r2_score(y_true, y_predict)
         pd.DataFrame(scaled_df, 
         columns=get_names)m                                                                                                                                                                                                              FURTHERMORE: 
                                                                                                                                                                                              Python for Data Science Certification Training Course