常见的降维技术比较：能否在不丢失信息的情况下降低数据维度

import pandas as pd  ## for data manipulation
df = pd.read_excel(r'Regression\AirQualityUCI.xlsx')
print(df.shape)
df.head()

X = df.drop(['CO(GT)', 'Date', 'Time'], axis=1)
y = df['CO(GT)']
X.shape, y.shape

#Output: ((9357, 12), (9357,))

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
X_train.shape, X_test.shape, y_train.shape, y_test.shape

#Output: ((7485, 12), (1872, 12), (7485,), (1872,))

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
X_train.shape, X_test.shape

from sklearn.decomposition import PCA
pca = PCA(n_components=0.95)
X_train_pca = pca.fit_transform(X_train)
X_test_pca = pca.transform(X_test)
X_train_pca

from sklearn.decomposition import TruncatedSVD
svd = TruncatedSVD(n_components=int(X_train.shape[1]*0.33))
X_train_svd = svd.fit_transform(X_train)
X_test_svd = svd.transform(X_test)
X_train_svd

import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.neighbors import KNeighborsRegressor
from sklearn.svm import SVR
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from sklearn.metrics import r2_score, mean_squared_error
import time

def train_test_ML(dataset, dataform, X_train, y_train, X_test, y_test):
    temp_df = pd.DataFrame(columns=['Data Set', 'Data Form', 'Dimensions', 'Model', 'R2 Score', 'RMSE', 'Time Taken'])
    for i in [LinearRegression, KNeighborsRegressor, SVR, DecisionTreeRegressor, RandomForestRegressor, GradientBoostingRegressor]:
        start_time = time.time()
        reg = i().fit(X_train, y_train)
        y_pred = reg.predict(X_test)
        r2 = np.round(r2_score(y_test, y_pred), 2)
        rmse = np.round(np.sqrt(mean_squared_error(y_test, y_pred)), 2)
        end_time = time.time()
        time_taken = np.round((end_time - start_time), 2)
        temp_df.loc[len(temp_df)] = [dataset, dataform, X_train.shape[1], str(i).split('.')[-1][:-2], r2, rmse, time_taken]
    return temp_df

original_df = train_test_ML('AirQualityUCI', 'Original', X_train, y_train, X_test, y_test)
original_df

pca_df = train_test_ML('AirQualityUCI', 'PCA Reduced', X_train_pca, y_train, X_test_pca, y_test)
pca_df

svd_df = train_test_ML('AirQualityUCI', 'SVD Reduced', X_train_svd, y_train, X_test_svd, y_test)
svd_df

from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.metrics import accuracy_score, f1_score, recall_score, precision_score

def train_test_ML2(dataset, dataform, X_train, y_train, X_test, y_test):
    temp_df = pd.DataFrame(columns=['Data Set', 'Data Form', 'Dimensions', 'Model', 'Accuracy', 'F1 Score', 'Recall', 'Precision', 'Time Taken'])
    for i in [LogisticRegression, KNeighborsClassifier, SVC, DecisionTreeClassifier, RandomForestClassifier, GradientBoostingClassifier]:
        start_time = time.time()
        reg = i().fit(X_train, y_train)
        y_pred = reg.predict(X_test)
        accuracy = np.round(accuracy_score(y_test, y_pred), 2)
        f1 = np.round(f1_score(y_test, y_pred, average='weighted'), 2)
        recall = np.round(recall_score(y_test, y_pred, average='weighted'), 2)
        precision = np.round(precision_score(y_test, y_pred, average='weighted'), 2)
        end_time = time.time()
        time_taken = np.round((end_time - start_time), 2)
        temp_df.loc[len(temp_df)] = [dataset, dataform, X_train.shape[1], str(i).split('.')[-1][:-2], accuracy, f1, recall, precision, time_taken]
    return temp_df

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

lda = LinearDiscriminantAnalysis()
X_train_lda = lda.fit_transform(X_train, y_train)
X_test_lda = lda.transform(X_test)