Python preprocessing.RobustScaler类代码示例

def scale_feature_matrix(feature_M, linear=False, outliers=False):
    from sklearn.preprocessing import StandardScaler, RobustScaler
    import numpy as np
    
    binary_fields = [col for col in feature_M.columns if len(set(feature_M[col])) == 2]
            
    if outliers:
        #Scaling 0 median & unit variance
        scaler_obj = RobustScaler()
        print 'centering around median'

    else:
        #Scale 0 mean & unit variance
        scaler_obj = StandardScaler()
        print 'centering around mean'
    
    print 'found these binaries'
    print '-' * 10
    print '\n'.join(binary_fields)

        
    X_scaled = scaler_obj.fit_transform(feature_M.drop(binary_fields, axis=1))
    X_scaled_w_cats = np.c_[X_scaled, feature_M[binary_fields].as_matrix()]
    
    return X_scaled_w_cats, scaler_obj

    def _robust_scaler(self, input_df):
        """Uses Scikit-learn's RobustScaler to scale the features using statistics that are robust to outliers

        Parameters
        ----------
        input_df: pandas.DataFrame {n_samples, n_features+['class', 'group', 'guess']}
            Input DataFrame to scale

        Returns
        -------
        scaled_df: pandas.DataFrame {n_samples, n_features + ['guess', 'group', 'class']}
            Returns a DataFrame containing the scaled features

        """
        training_features = input_df.loc[input_df['group'] == 'training'].drop(['class', 'group', 'guess'], axis=1)

        if len(training_features.columns.values) == 0:
            return input_df.copy()

        # The scaler must be fit on only the training data
        scaler = RobustScaler()
        scaler.fit(training_features.values.astype(np.float64))
        scaled_features = scaler.transform(input_df.drop(['class', 'group', 'guess'], axis=1).values.astype(np.float64))

        for col_num, column in enumerate(input_df.drop(['class', 'group', 'guess'], axis=1).columns.values):
            input_df.loc[:, column] = scaled_features[:, col_num]

        return input_df.copy()

def processing(df):
    dummies_df = pd.get_dummies(df["City Group"])

    def add_CG(name):
        return "CG_" + name

    dummies_df = dummies_df.rename(columns=add_CG)
    # print dummies_df.head()
    df = pd.concat([df, dummies_df.iloc[:, 0]], axis=1)

    dummies_df = pd.get_dummies(df["Type"])

    def add_Type(name):
        return "Type_" + name

    dummies_df = dummies_df.rename(columns=add_Type)
    df = pd.concat([df, dummies_df.iloc[:, 0:3]], axis=1)

    # try to put in age as a column
    def add_Age(string):
        age = datetime.datetime.now() - datetime.datetime.strptime(string, "%m/%d/%Y")
        return age.days

    df["Age"] = df["Open Date"].map(add_Age)
    df = df.drop(["Id", "Open Date", "City", "City Group", "Type", "revenue"], axis=1)
    # scaler = StandardScaler().fit(df)
    scaler = RobustScaler().fit(df)
    df = scaler.transform(df)

    # print df.head()
    return df

    def ica_analysis(self, X_train, X_test, y_train, y_test, data_set_name):
        scl = RobustScaler()
        X_train_scl = scl.fit_transform(X_train)
        X_test_scl = scl.transform(X_test)
        
        ##
        ## ICA
        ##
        ica = FastICA(n_components=X_train_scl.shape[1])
        X_ica = ica.fit_transform(X_train_scl)
        
        ##
        ## Plots
        ##
        ph = plot_helper()

        kurt = kurtosis(X_ica)
        print(kurt)
        
        title = 'Kurtosis (FastICA) for ' + data_set_name
        name = data_set_name.lower() + '_ica_kurt'
        filename = './' + self.out_dir + '/' + name + '.png'
        
        ph.plot_simple_bar(np.arange(1, len(kurt)+1, 1),
                           kurt,
                           np.arange(1, len(kurt)+1, 1).astype('str'),
                           'Feature Index',
                           'Kurtosis',
                           title,
                           filename)

 def best_ica_wine(self):
     dh = data_helper()
     X_train, X_test, y_train, y_test = dh.get_wine_data()
     
     scl = RobustScaler()
     X_train_scl = scl.fit_transform(X_train)
     X_test_scl = scl.transform(X_test)
     
     ica = FastICA(n_components=X_train_scl.shape[1])
     X_train_transformed = ica.fit_transform(X_train_scl, y_train)
     X_test_transformed = ica.transform(X_test_scl)
     
     ## top 2
     kurt = kurtosis(X_train_transformed)
     i = kurt.argsort()[::-1]
     X_train_transformed_sorted = X_train_transformed[:, i]
     X_train_transformed = X_train_transformed_sorted[:,0:2]
     
     kurt = kurtosis(X_test_transformed)
     i = kurt.argsort()[::-1]
     X_test_transformed_sorted = X_test_transformed[:, i]
     X_test_transformed = X_test_transformed_sorted[:,0:2]
     
     # save
     filename = './' + self.save_dir + '/wine_ica_x_train.txt'
     pd.DataFrame(X_train_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_ica_x_test.txt'
     pd.DataFrame(X_test_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_ica_y_train.txt'
     pd.DataFrame(y_train).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_ica_y_test.txt'
     pd.DataFrame(y_test).to_csv(filename, header=False, index=False)

 def best_rp_nba(self):
     dh = data_helper()
     X_train, X_test, y_train, y_test = dh.get_nba_data()
     
     scl = RobustScaler()
     X_train_scl = scl.fit_transform(X_train)
     X_test_scl = scl.transform(X_test)
     
     rp = GaussianRandomProjection(n_components=X_train_scl.shape[1])
     X_train_transformed = rp.fit_transform(X_train_scl, y_train)
     X_test_transformed = rp.transform(X_test_scl)
     
     ## top 2
     kurt = kurtosis(X_train_transformed)
     i = kurt.argsort()[::-1]
     X_train_transformed_sorted = X_train_transformed[:, i]
     X_train_transformed = X_train_transformed_sorted[:,0:2]
     
     kurt = kurtosis(X_test_transformed)
     i = kurt.argsort()[::-1]
     X_test_transformed_sorted = X_test_transformed[:, i]
     X_test_transformed = X_test_transformed_sorted[:,0:2]
     
     # save
     filename = './' + self.save_dir + '/nba_rp_x_train.txt'
     pd.DataFrame(X_train_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/nba_rp_x_test.txt'
     pd.DataFrame(X_test_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/nba_rp_y_train.txt'
     pd.DataFrame(y_train).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/nba_rp_y_test.txt'
     pd.DataFrame(y_test).to_csv(filename, header=False, index=False)

def num_scaler(d_num,t_num):
    scl = RobustScaler()
    scl.fit(d_num)
    d_num = scl.transform(d_num)
    t_num = scl.transform(t_num)
    
    return d_num, t_num

 def rp_analysis(self, X_train, X_test, y_train, y_test, data_set_name):
     scl = RobustScaler()
     X_train_scl = scl.fit_transform(X_train)
     
     ks = []
     for i in range(1000):
         ##
         ## Random Projection
         ##
         rp = GaussianRandomProjection(n_components=X_train_scl.shape[1])
         rp.fit(X_train_scl)
         X_train_rp = rp.transform(X_train_scl)
         
         ks.append(kurtosis(X_train_rp))
         
     mean_k = np.mean(ks, 0)
         
     ##
     ## Plots
     ##
     ph = plot_helper()
     
     title = 'Kurtosis (Randomized Projection) for ' + data_set_name
     name = data_set_name.lower() + '_rp_kurt'
     filename = './' + self.out_dir + '/' + name + '.png'
     
     ph.plot_simple_bar(np.arange(1, len(mean_k)+1, 1),
                        mean_k,
                        np.arange(1, len(mean_k)+1, 1).astype('str'),
                        'Feature Index',
                        'Kurtosis',
                        title,
                        filename)

 def nn_wine_orig(self):
     dh = data_helper()
     X_train, X_test, y_train, y_test = dh.get_wine_data()
     
     scl = RobustScaler()
     X_train_scl = scl.fit_transform(X_train)
     X_test_scl = scl.transform(X_test)
     
     self.part4.nn_analysis(X_train_scl, X_test_scl, y_train, y_test, 'Wine', 'Neural Network Original')

def standardize_columns(data):
    """
    We decided to standardize the weather factor due to outliers.
    """
    columns_to_standardize = ['temp', 'atemp', 'humidity', 'windspeed']
    min_max_scaler = RobustScaler()

    for column in columns_to_standardize:
        data[column] = min_max_scaler.fit_transform(data[column])
    return data

 def lda_analysis(self, X_train, X_test, y_train, y_test, data_set_name):
     scl = RobustScaler()
     X_train_scl = scl.fit_transform(X_train)
     X_test_scl = scl.transform(X_test)
     
     ##
     ## Plots
     ##
     ph = plot_helper()
     
     scores = []
     train_scores = []
     rng = range(1, X_train_scl.shape[1]+1)
     for i in rng:
         lda = LinearDiscriminantAnalysis(n_components=i)
         cv = KFold(X_train_scl.shape[0], 3, shuffle=True)
         
         # cross validation
         cv_scores = []
         for (train, test) in cv:
             lda.fit(X_train_scl[train], y_train[train])
             score = lda.score(X_train_scl[test], y_train[test])
             cv_scores.append(score)
         
         mean_score = np.mean(cv_scores)
         scores.append(mean_score)
         
         # train score
         lda = LinearDiscriminantAnalysis(n_components=i)
         lda.fit(X_train_scl, y_train)
         train_score = lda.score(X_train_scl, y_train)
         train_scores.append(train_score)
         
         print(i, mean_score)
         
     ##
     ## Score Plot
     ##
     title = 'Score Summary Plot (LDA) for ' + data_set_name
     name = data_set_name.lower() + '_lda_score'
     filename = './' + self.out_dir + '/' + name + '.png'
                 
     ph.plot_series(rng,
                    [scores, train_scores],
                    [None, None],
                    ['cross validation score', 'training score'],
                    cm.viridis(np.linspace(0, 1, 2)),
                    ['o', '*'],
                    title,
                    'n_components',
                    'Score',
                    filename)

def demensionReduction(numFeatures,cateFeatures):
    """

    :param numFeatures:
    :param labels:
    :return:
    """
    scaler = RobustScaler()
    scaledFeatures = scaler.fit_transform(numFeatures)
    pca = PCA(n_components=5)
    reducedFeatures = pca.fit_transform(scaledFeatures)
    allFeatures = np.concatenate((reducedFeatures,cateFeatures),axis=1)
    return allFeatures

def test_robustscaler_vs_sklearn():
    # Compare msmbuilder.preprocessing.RobustScaler
    # with sklearn.preprocessing.RobustScaler

    robustscalerr = RobustScalerR()
    robustscalerr.fit(np.concatenate(trajs))

    robustscaler = RobustScaler()
    robustscaler.fit(trajs)

    y_ref1 = robustscalerr.transform(trajs[0])
    y1 = robustscaler.transform(trajs)[0]

    np.testing.assert_array_almost_equal(y_ref1, y1)

 def best_lda_cluster_wine(self):
     dh = data_helper()
     dh = data_helper()
     X_train, X_test, y_train, y_test = dh.get_wine_data_lda_best()
     
     scl = RobustScaler()
     X_train_scl = scl.fit_transform(X_train)
     X_test_scl = scl.transform(X_test)
     
     ##
     ## K-Means
     ##
     km = KMeans(n_clusters=4, algorithm='full')
     X_train_transformed = km.fit_transform(X_train_scl)
     X_test_transformed = km.transform(X_test_scl)
     
     # save
     filename = './' + self.save_dir + '/wine_kmeans_lda_x_train.txt'
     pd.DataFrame(X_train_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_kmeans_lda_x_test.txt'
     pd.DataFrame(X_test_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_kmeans_lda_y_train.txt'
     pd.DataFrame(y_train).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_kmeans_lda_y_test.txt'
     pd.DataFrame(y_test).to_csv(filename, header=False, index=False)
     
     ##
     ## GMM
     ##
     gmm = GaussianMixture(n_components=4, covariance_type='full')
     X_train_transformed = km.fit_transform(X_train_scl)
     X_test_transformed = km.transform(X_test_scl)
     
     # save
     filename = './' + self.save_dir + '/wine_gmm_lda_x_train.txt'
     pd.DataFrame(X_train_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_gmm_lda_x_test.txt'
     pd.DataFrame(X_test_transformed).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_gmm_lda_y_train.txt'
     pd.DataFrame(y_train).to_csv(filename, header=False, index=False)
     
     filename = './' + self.save_dir + '/wine_gmm_lda_y_test.txt'
     pd.DataFrame(y_test).to_csv(filename, header=False, index=False)

def transform_dataframe(dataframe):

    """
    Function to read dataframe and standardize the dataframe with
    a mean 0 and unit variance on every column

    Parameters:
        dataframe : Input pandas dataframe
    Input types: pd.Dataframe
    Output types: pd.Dataframe

    """
    cols = [col for col in dataframe.columns]
    robust_scaler = RobustScaler()
    df = robust_scaler.fit_transform(dataframe[cols])
    dataframe.columns = df
    return dataframe