{"id":1155766,"date":"2025-01-13T18:07:47","date_gmt":"2025-01-13T10:07:47","guid":{"rendered":""},"modified":"2025-01-13T18:07:49","modified_gmt":"2025-01-13T10:07:49","slug":"python%e5%a6%82%e4%bd%95%e7%9c%8b%e6%95%b0%e6%8d%ae%e7%89%b9%e5%be%81","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1155766.html","title":{"rendered":"python\u5982\u4f55\u770b\u6570\u636e\u7279\u5f81"},"content":{"rendered":"

\"python\u5982\u4f55\u770b\u6570\u636e\u7279\u5f81\"<\/p>\n

\u8981\u5728Python\u4e2d\u67e5\u770b\u6570\u636e\u7279\u5f81\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u3001NumPy\u3001scikit-learn<\/strong>\u7b49\u5e93\u3001Seaborn<\/strong>\u8fdb\u884c\u53ef\u89c6\u5316\u3001\u63cf\u8ff0\u6027\u7edf\u8ba1\u5206\u6790<\/strong>\u3002\u8fd9\u4e9b\u65b9\u6cd5\u53ef\u4ee5\u5e2e\u52a9\u4f60\u6df1\u5165\u4e86\u89e3\u6570\u636e\u96c6\u7684\u7ed3\u6784\u548c\u7279\u6027\u3002pandas<\/strong>\u662f\u6570\u636e\u5904\u7406\u7684\u4e3b\u8981\u5de5\u5177\uff0cNumPy<\/strong>\u7528\u4e8e\u6570\u503c\u8fd0\u7b97\uff0cscikit-learn<\/strong>\u63d0\u4f9b\u4e86\u673a\u5668\u5b66\u4e60<\/a>\u5de5\u5177\uff0cSeaborn<\/strong>\u7528\u4e8e\u7ed8\u5236\u7edf\u8ba1\u56fe\u8868\u3002\u4e0b\u9762\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u8fd9\u4e9b\u5de5\u5177\u67e5\u770b\u6570\u636e\u7279\u5f81\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528pandas\u5e93<\/h3>\n<\/p>\n

1. \u5bfc\u5165\u6570\u636e<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5bfc\u5165\u6570\u636e\u3002pandas\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684I\/O\u63a5\u53e3\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bfb\u53d6\u5404\u79cd\u683c\u5f0f\u7684\u6587\u4ef6\uff0c\u5982CSV\u3001Excel\u3001SQL\u6570\u636e\u5e93\u7b49\u3002<\/p>\n<\/p>\n

import pandas as pd<\/p>\n
\u4eceCSV\u6587\u4ef6\u5bfc\u5165\u6570\u636e<\/strong><\/h2>\n
df = pd.read_csv('path_to_your_file.csv')<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u67e5\u770b\u57fa\u672c\u4fe1\u606f<\/h4>\n<\/p>\n
\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u65b9\u6cd5\u67e5\u770b\u6570\u636e\u7684\u57fa\u672c\u4fe1\u606f\uff1a<\/p>\n<\/p>\n
# \u67e5\u770b\u524d5\u884c\u6570\u636e<\/p>\n
print(df.head())<\/p>\n
\u67e5\u770b\u6570\u636e\u57fa\u672c\u4fe1\u606f\uff0c\u5305\u62ec\u6bcf\u5217\u7684\u6570\u636e\u7c7b\u578b\u548c\u975e\u7a7a\u503c\u6570\u91cf<\/strong><\/h2>\n
print(df.info())<\/p>\n
\u67e5\u770b\u6570\u636e\u7684\u7edf\u8ba1\u4fe1\u606f<\/strong><\/h2>\n
print(df.describe())<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u68c0\u67e5\u7f3a\u5931\u503c<\/h4>\n<\/p>\n
\u7f3a\u5931\u503c\u662f\u6570\u636e\u5206\u6790\u4e2d\u5e38\u89c1\u7684\u95ee\u9898\uff0cpandas\u63d0\u4f9b\u4e86\u65b9\u4fbf\u7684\u65b9\u6cd5\u6765\u68c0\u67e5\u548c\u5904\u7406\u7f3a\u5931\u503c\uff1a<\/p>\n<\/p>\n
# \u68c0\u67e5\u6bcf\u5217\u7684\u7f3a\u5931\u503c\u6570\u91cf<\/p>\n
print(df.isnull().sum())<\/p>\n
\u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c<\/strong><\/h2>\n
df.dropna(inplace=True)<\/p>\n
\u7528\u67d0\u4e2a\u503c\u586b\u5145\u7f3a\u5931\u503c<\/strong><\/h2>\n
df.fillna(0, inplace=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528NumPy\u5e93<\/h3>\n<\/p>\n
NumPy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6570\u503c\u8ba1\u7b97\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u9ad8\u6548\u7684\u6570\u7ec4\u64cd\u4f5c\u3002\u6211\u4eec\u53ef\u4ee5\u5c06pandas DataFrame\u8f6c\u6362\u4e3aNumPy\u6570\u7ec4\uff0c\u4ee5\u4fbf\u8fdb\u884c\u9ad8\u6548\u7684\u6570\u503c\u8ba1\u7b97\uff1a<\/p>\n<\/p>\n
import numpy as np<\/p>\n
\u5c06DataFrame\u8f6c\u6362\u4e3aNumPy\u6570\u7ec4<\/strong><\/h2>\n
data_array = df.values<\/p>\n
\u8ba1\u7b97\u5747\u503c<\/strong><\/h2>\n
mean = np.mean(data_array, axis=0)<\/p>\n
\u8ba1\u7b97\u6807\u51c6\u5dee<\/strong><\/h2>\n
std_dev = np.std(data_array, axis=0)<\/p>\n
print("Mean:", mean)<\/p>\n
print("Standard Deviation:", std_dev)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528scikit-learn\u5e93<\/h3>\n<\/p>\n
scikit-learn\u662f\u4e00\u4e2a\u673a\u5668\u5b66\u4e60\u5e93\uff0c\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u6570\u636e\u9884\u5904\u7406\u5de5\u5177\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u5b83\u6765\u6807\u51c6\u5316\u6570\u636e\u3001\u8fdb\u884c\u7279\u5f81\u9009\u62e9\u7b49\uff1a<\/p>\n<\/p>\n
1. \u6807\u51c6\u5316\u6570\u636e<\/h4>\n<\/p>\n
\u6807\u51c6\u5316\u662f\u5c06\u6570\u636e\u8f6c\u6362\u4e3a\u5747\u503c\u4e3a0\u3001\u6807\u51c6\u5dee\u4e3a1\u7684\u6570\u636e\uff1a<\/p>\n<\/p>\n
from sklearn.preprocessing import StandardScaler<\/p>\n
scaler = StandardScaler()<\/p>\n
scaled_data = scaler.fit_transform(df)<\/p>\n
print("Scaled Data:", scaled_data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7279\u5f81\u9009\u62e9<\/h4>\n<\/p>\n
\u7279\u5f81\u9009\u62e9\u662f\u4ece\u6570\u636e\u96c6\u4e2d\u9009\u62e9\u6700\u91cd\u8981\u7684\u7279\u5f81\uff0c\u4ee5\u63d0\u9ad8\u6a21\u578b\u7684\u6027\u80fd\u548c\u53ef\u89e3\u91ca\u6027\uff1a<\/p>\n<\/p>\n
from sklearn.feature_selection import SelectKBest, f_classif<\/p>\n
\u9009\u62e9\u524d5\u4e2a\u6700\u91cd\u8981\u7684\u7279\u5f81<\/strong><\/h2>\n
selector = SelectKBest(f_classif, k=5)<\/p>\n
selected_features = selector.fit_transform(df.iloc[:, :-1], df.iloc[:, -1])<\/p>\n
print("Selected Features:", selected_features)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u4f7f\u7528Seaborn\u8fdb\u884c\u6570\u636e\u53ef\u89c6\u5316<\/h3>\n<\/p>\n
Seaborn\u662f\u4e00\u4e2a\u57fa\u4e8eMatplotlib\u7684\u6570\u636e\u53ef\u89c6\u5316\u5e93\uff0c\u63d0\u4f9b\u4e86\u7b80\u6d01\u7684\u63a5\u53e3\u6765\u7ed8\u5236\u5404\u79cd\u7edf\u8ba1\u56fe\u8868\uff1a<\/p>\n<\/p>\n
1. \u7ed8\u5236\u5206\u5e03\u56fe<\/h4>\n<\/p>\n
\u5206\u5e03\u56fe\u7528\u4e8e\u67e5\u770b\u6570\u636e\u7684\u5206\u5e03\u60c5\u51b5\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u53d1\u73b0\u6570\u636e\u662f\u5426\u9075\u5faa\u67d0\u79cd\u5206\u5e03\uff1a<\/p>\n<\/p>\n
import seaborn as sns<\/p>\n
import matplotlib.pyplot as plt<\/p>\n
\u7ed8\u5236\u5355\u53d8\u91cf\u5206\u5e03\u56fe<\/strong><\/h2>\n
sns.histplot(df['column_name'], kde=True)<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7ed8\u5236\u76f8\u5173\u77e9\u9635<\/h4>\n<\/p>\n
\u76f8\u5173\u77e9\u9635\u7528\u4e8e\u67e5\u770b\u5404\u7279\u5f81\u4e4b\u95f4\u7684\u76f8\u5173\u6027\uff0c\u6709\u52a9\u4e8e\u53d1\u73b0\u7279\u5f81\u4e4b\u95f4\u7684\u7ebf\u6027\u5173\u7cfb\uff1a<\/p>\n<\/p>\n
# \u8ba1\u7b97\u76f8\u5173\u77e9\u9635<\/p>\n
corr_matrix = df.corr()<\/p>\n
\u7ed8\u5236\u70ed\u56fe<\/strong><\/h2>\n
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm')<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u63cf\u8ff0\u6027\u7edf\u8ba1\u5206\u6790<\/h3>\n<\/p>\n
\u63cf\u8ff0\u6027\u7edf\u8ba1\u5206\u6790\u662f\u5bf9\u6570\u636e\u8fdb\u884c\u7b80\u8981\u63cf\u8ff0\u548c\u603b\u7ed3\u7684\u4e00\u79cd\u65b9\u6cd5\uff0c\u5305\u62ec\u5747\u503c\u3001\u6807\u51c6\u5dee\u3001\u6700\u5c0f\u503c\u3001\u6700\u5927\u503c\u7b49\u6307\u6807\uff1a<\/p>\n<\/p>\n
# \u8ba1\u7b97\u5747\u503c<\/p>\n
mean = df.mean()<\/p>\n
\u8ba1\u7b97\u6807\u51c6\u5dee<\/strong><\/h2>\n
std_dev = df.std()<\/p>\n
\u8ba1\u7b97\u6700\u5c0f\u503c<\/strong><\/h2>\n
min_val = df.min()<\/p>\n
\u8ba1\u7b97\u6700\u5927\u503c<\/strong><\/h2>\n
max_val = df.max()<\/p>\n
print("Mean:", mean)<\/p>\n
print("Standard Deviation:", std_dev)<\/p>\n
print("Min:", min_val)<\/p>\n
print("Max:", max_val)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u68c0\u67e5\u5206\u5e03\u548c\u5f02\u5e38\u503c<\/h3>\n<\/p>\n
\u5728\u6570\u636e\u5206\u6790\u4e2d\uff0c\u68c0\u67e5\u6570\u636e\u7684\u5206\u5e03\u548c\u5f02\u5e38\u503c\u662f\u975e\u5e38\u91cd\u8981\u7684\u4e00\u6b65\u3002\u5f02\u5e38\u503c\u4f1a\u5bf9\u6a21\u578b\u7684\u8bad\u7ec3\u548c\u9884\u6d4b\u4ea7\u751f\u8f83\u5927\u7684\u5f71\u54cd\uff0c\u56e0\u6b64\u5728\u7279\u5f81\u5de5\u7a0b\u548c\u6570\u636e\u9884\u5904\u7406\u4e2d\u9700\u8981\u7279\u522b\u6ce8\u610f\u3002<\/p>\n<\/p>\n
1. \u7ed8\u5236\u7bb1\u7ebf\u56fe<\/h4>\n<\/p>\n
\u7bb1\u7ebf\u56fe\uff08Box Plot\uff09\u662f\u4e00\u79cd\u663e\u793a\u6570\u636e\u5206\u5e03\u7684\u56fe\u8868\uff0c\u53ef\u4ee5\u6e05\u6670\u5730\u663e\u793a\u6570\u636e\u7684\u4e2d\u4f4d\u6570\u3001\u56db\u5206\u4f4d\u6570\u4ee5\u53ca\u5f02\u5e38\u503c\uff1a<\/p>\n<\/p>\n
# \u7ed8\u5236\u7bb1\u7ebf\u56fe<\/p>\n
sns.boxplot(data=df)<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7ed8\u5236\u5c0f\u63d0\u7434\u56fe<\/h4>\n<\/p>\n
\u5c0f\u63d0\u7434\u56fe\uff08Violin Plot\uff09\u7ed3\u5408\u4e86\u7bb1\u7ebf\u56fe\u548c\u5bc6\u5ea6\u56fe\u7684\u7279\u6027\uff0c\u53ef\u4ee5\u540c\u65f6\u5c55\u793a\u6570\u636e\u7684\u5206\u5e03\u3001\u6982\u7387\u5bc6\u5ea6\u548c\u5f02\u5e38\u503c\uff1a<\/p>\n<\/p>\n
# \u7ed8\u5236\u5c0f\u63d0\u7434\u56fe<\/p>\n
sns.violinplot(data=df)<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u6570\u636e\u7684\u5206\u7ec4\u548c\u805a\u5408<\/h3>\n<\/p>\n
\u5728\u6570\u636e\u5206\u6790\u4e2d\uff0c\u7ecf\u5e38\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u548c\u805a\u5408\u64cd\u4f5c\u3002pandas\u5e93\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u5206\u7ec4\u548c\u805a\u5408\u529f\u80fd\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5feb\u901f\u5730\u5bf9\u6570\u636e\u8fdb\u884c\u7edf\u8ba1\u5206\u6790\u3002<\/p>\n<\/p>\n
1. \u6309\u5355\u4e00\u7279\u5f81\u5206\u7ec4<\/h4>\n<\/p>\n
# \u6309\u67d0\u4e00\u5217\u5206\u7ec4\u5e76\u8ba1\u7b97\u5747\u503c<\/p>\n
grouped = df.groupby('column_name').mean()<\/p>\n
print(grouped)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u6309\u591a\u7279\u5f81\u5206\u7ec4<\/h4>\n<\/p>\n
# \u6309\u591a\u5217\u5206\u7ec4\u5e76\u8ba1\u7b97\u7edf\u8ba1\u91cf<\/p>\n
grouped = df.groupby(['column1', 'column2']).agg(['mean', 'sum'])<\/p>\n
print(grouped)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u65f6\u95f4\u5e8f\u5217\u6570\u636e\u5206\u6790<\/h3>\n<\/p>\n
\u5bf9\u4e8e\u65f6\u95f4\u5e8f\u5217\u6570\u636e\uff0cpandas\u63d0\u4f9b\u4e86\u4e13\u95e8\u7684\u65f6\u95f4\u5e8f\u5217\u5904\u7406\u529f\u80fd\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8fdb\u884c\u65f6\u95f4\u5e8f\u5217\u5206\u6790\u3002<\/p>\n<\/p>\n
1. \u8bbe\u7f6e\u65f6\u95f4\u7d22\u5f15<\/h4>\n<\/p>\n
# \u5c06\u67d0\u4e00\u5217\u8bbe\u7f6e\u4e3a\u65f6\u95f4\u7d22\u5f15<\/p>\n
df['date_column'] = pd.to_datetime(df['date_column'])<\/p>\n
df.set_index('date_column', inplace=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8fdb\u884c\u6eda\u52a8\u8ba1\u7b97<\/h4>\n<\/p>\n
# \u8ba1\u7b97\u6eda\u52a8\u5e73\u5747<\/p>\n
rolling_mean = df['value_column'].rolling(window=7).mean()<\/p>\n
print(rolling_mean)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e5d\u3001\u4f7f\u7528\u9ad8\u7ea7\u6570\u636e\u5206\u6790\u5de5\u5177<\/h3>\n<\/p>\n
\u5728\u5b9e\u9645\u7684\u6570\u636e\u5206\u6790\u8fc7\u7a0b\u4e2d\uff0c\u8fd8\u53ef\u4ee5\u501f\u52a9\u66f4\u591a\u7684\u9ad8\u7ea7\u6570\u636e\u5206\u6790\u5de5\u5177\u6765\u8fdb\u4e00\u6b65\u6316\u6398\u6570\u636e\u7279\u5f81\u3002<\/p>\n<\/p>\n
1. \u4f7f\u7528PCA\u8fdb\u884c\u964d\u7ef4<\/h4>\n<\/p>\n
\u4e3b\u6210\u5206\u5206\u6790\uff08PCA\uff09\u662f\u4e00\u79cd\u5e38\u7528\u7684\u964d\u7ef4\u6280\u672f\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u51cf\u5c11\u6570\u636e\u7684\u7ef4\u5ea6\uff0c\u540c\u65f6\u4fdd\u7559\u5c3d\u53ef\u80fd\u591a\u7684\u4fe1\u606f\uff1a<\/p>\n<\/p>\n
from sklearn.decomposition import PCA<\/p>\n
pca = PCA(n_components=2)<\/p>\n
pca_result = pca.fit_transform(df)<\/p>\n
print("PCA Result:", pca_result)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528t-SNE\u8fdb\u884c\u6570\u636e\u53ef\u89c6\u5316<\/h4>\n<\/p>\n
t-SNE\uff08t-Distributed Stochastic Neighbor Embedding\uff09\u662f\u4e00\u79cd\u975e\u7ebf\u6027\u964d\u7ef4\u6280\u672f\uff0c\u5e38\u7528\u4e8e\u9ad8\u7ef4\u6570\u636e\u7684\u53ef\u89c6\u5316\uff1a<\/p>\n<\/p>\n
from sklearn.manifold import TSNE<\/p>\n
tsne = TSNE(n_components=2)<\/p>\n
tsne_result = tsne.fit_transform(df)<\/p>\n
print("t-SNE Result:", tsne_result)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5341\u3001\u7279\u5f81\u5de5\u7a0b<\/h3>\n<\/p>\n
\u7279\u5f81\u5de5\u7a0b\u662f\u673a\u5668\u5b66\u4e60\u4e2d\u975e\u5e38\u91cd\u8981\u7684\u4e00\u73af\uff0c\u901a\u8fc7\u5bf9\u539f\u59cb\u6570\u636e\u8fdb\u884c\u8f6c\u6362\u548c\u5904\u7406\uff0c\u53ef\u4ee5\u751f\u6210\u66f4\u6709\u610f\u4e49\u7684\u7279\u5f81\uff0c\u4ece\u800c\u63d0\u5347\u6a21\u578b\u7684\u6027\u80fd\u3002<\/p>\n<\/p>\n
1. \u7279\u5f81\u7f16\u7801<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u5206\u7c7b\u53d8\u91cf\uff0c\u53ef\u4ee5\u4f7f\u7528\u72ec\u70ed\u7f16\u7801\uff08One-Hot Encoding\uff09\u5c06\u5176\u8f6c\u6362\u4e3a\u6570\u503c\u578b\u7279\u5f81\uff1a<\/p>\n<\/p>\n
# \u4f7f\u7528pandas\u7684get_dummies\u8fdb\u884c\u72ec\u70ed\u7f16\u7801<\/p>\n
encoded_df = pd.get_dummies(df, columns=['categorical_column'])<\/p>\n
print(encoded_df)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7279\u5f81\u4ea4\u4e92<\/h4>\n<\/p>\n
\u7279\u5f81\u4ea4\u4e92\u662f\u6307\u901a\u8fc7\u5bf9\u73b0\u6709\u7279\u5f81\u8fdb\u884c\u7ec4\u5408\u751f\u6210\u65b0\u7684\u7279\u5f81\uff1a<\/p>\n<\/p>\n
# \u751f\u6210\u4e24\u4e2a\u7279\u5f81\u7684\u4e58\u79ef<\/p>\n
df['new_feature'] = df['feature1'] * df['feature2']<\/p>\n
print(df)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5341\u4e00\u3001\u7279\u5f81\u9009\u62e9\u4e0e\u91cd\u8981\u6027\u8bc4\u4f30<\/h3>\n<\/p>\n
\u5728\u9ad8\u7ef4\u6570\u636e\u96c6\u4e2d\uff0c\u7279\u5f81\u9009\u62e9\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u6311\u9009\u51fa\u5bf9\u6a21\u578b\u5f71\u54cd\u6700\u5927\u7684\u7279\u5f81\uff0c\u4ece\u800c\u63d0\u9ad8\u6a21\u578b\u7684\u6027\u80fd\u548c\u53ef\u89e3\u91ca\u6027\u3002<\/p>\n<\/p>\n
1. \u4f7f\u7528Lasso\u8fdb\u884c\u7279\u5f81\u9009\u62e9<\/h4>\n<\/p>\n
Lasso\u56de\u5f52\u662f\u4e00\u79cd\u5e26L1\u6b63\u5219\u5316\u7684\u7ebf\u6027\u56de\u5f52\u6a21\u578b\uff0c\u53ef\u4ee5\u7528\u4e8e\u7279\u5f81\u9009\u62e9\uff1a<\/p>\n<\/p>\n
from sklearn.linear_model import Lasso<\/p>\n
lasso = Lasso(alpha=0.01)<\/p>\n
lasso.fit(df.iloc[:, :-1], df.iloc[:, -1])<\/p>\n
print("Selected Features:", lasso.coef_)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528\u968f\u673a\u68ee\u6797\u8fdb\u884c\u7279\u5f81\u91cd\u8981\u6027\u8bc4\u4f30<\/h4>\n<\/p>\n
\u968f\u673a\u68ee\u6797\u662f\u4e00\u79cd\u96c6\u6210\u5b66\u4e60\u6a21\u578b\uff0c\u901a\u8fc7\u8bc4\u4f30\u7279\u5f81\u5728\u6811\u4e2d\u7684\u91cd\u8981\u6027\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8fdb\u884c\u7279\u5f81\u9009\u62e9\uff1a<\/p>\n<\/p>\n
from sklearn.ensemble import RandomForestRegressor<\/p>\n
rf = RandomForestRegressor()<\/p>\n
rf.fit(df.iloc[:, :-1], df.iloc[:, -1])<\/p>\n
print("Feature Importances:", rf.feature_importances_)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5341\u4e8c\u3001\u6570\u636e\u6e05\u6d17\u4e0e\u9884\u5904\u7406<\/h3>\n<\/p>\n
\u5728\u6570\u636e\u5206\u6790\u7684\u8fc7\u7a0b\u4e2d\uff0c\u6570\u636e\u6e05\u6d17\u4e0e\u9884\u5904\u7406\u662f\u975e\u5e38\u91cd\u8981\u7684\u4e00\u73af\u3002\u901a\u8fc7\u5904\u7406\u7f3a\u5931\u503c\u3001\u5f02\u5e38\u503c\u548c\u6570\u636e\u8f6c\u6362\uff0c\u53ef\u4ee5\u63d0\u9ad8\u6570\u636e\u7684\u8d28\u91cf\u548c\u5206\u6790\u7684\u51c6\u786e\u6027\u3002<\/p>\n<\/p>\n
1. \u5904\u7406\u7f3a\u5931\u503c<\/h4>\n<\/p>\n
\u7f3a\u5931\u503c\u5904\u7406\u53ef\u4ee5\u91c7\u7528\u5220\u9664\u3001\u586b\u5145\u7b49\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
# \u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c<\/p>\n
df.dropna(inplace=True)<\/p>\n
\u7528\u5747\u503c\u586b\u5145\u7f3a\u5931\u503c<\/strong><\/h2>\n
df.fillna(df.mean(), inplace=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u6570\u636e\u8f6c\u6362<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u6570\u503c\u578b\u7279\u5f81\uff0c\u53ef\u4ee5\u8fdb\u884c\u6807\u51c6\u5316\u548c\u5f52\u4e00\u5316\u5904\u7406\uff1a<\/p>\n<\/p>\n
from sklearn.preprocessing import StandardScaler, MinMaxScaler<\/p>\n
\u6807\u51c6\u5316<\/strong><\/h2>\n
scaler = StandardScaler()<\/p>\n
df_standardized = scaler.fit_transform(df)<\/p>\n
\u5f52\u4e00\u5316<\/strong><\/h2>\n
scaler = MinMaxScaler()<\/p>\n
df_normalized = scaler.fit_transform(df)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5341\u4e09\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u5168\u9762\u5730\u67e5\u770b\u548c\u5206\u6790\u6570\u636e\u7279\u5f81\u3002\u4f7f\u7528pandas\u8fdb\u884c\u6570\u636e\u5bfc\u5165\u3001\u67e5\u770b\u57fa\u672c\u4fe1\u606f\u548c\u5904\u7406\u7f3a\u5931\u503c\uff0c\u4f7f\u7528NumPy\u8fdb\u884c\u6570\u503c\u8fd0\u7b97\uff0c\u4f7f\u7528scikit-learn\u8fdb\u884c\u6570\u636e\u9884\u5904\u7406\u548c\u7279\u5f81\u9009\u62e9\uff0c\u4f7f\u7528Seaborn\u8fdb\u884c\u6570\u636e\u53ef\u89c6\u5316\uff0c\u8fdb\u884c\u63cf\u8ff0\u6027\u7edf\u8ba1\u5206\u6790\uff0c\u68c0\u67e5\u6570\u636e\u5206\u5e03\u548c\u5f02\u5e38\u503c\uff0c\u8fdb\u884c\u6570\u636e\u5206\u7ec4\u548c\u805a\u5408\uff0c\u5904\u7406\u65f6\u95f4\u5e8f\u5217\u6570\u636e\uff0c\u4f7f\u7528\u9ad8\u7ea7\u6570\u636e\u5206\u6790\u5de5\u5177\u8fdb\u884c\u964d\u7ef4\u548c\u53ef\u89c6\u5316\uff0c\u8fdb\u884c\u7279\u5f81\u5de5\u7a0b\u548c\u7279\u5f81\u9009\u62e9\uff0c\u8fdb\u884c\u6570\u636e\u6e05\u6d17\u4e0e\u9884\u5904\u7406\u3002\u8fd9\u4e9b\u65b9\u6cd5\u548c\u5de5\u5177\u76f8\u7ed3\u5408\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5168\u9762\u3001\u6df1\u5165\u5730\u4e86\u89e3\u6570\u636e\u7279\u5f81\uff0c\u4ece\u800c\u4e3a\u540e\u7eed\u7684\u6570\u636e\u5206\u6790\u548c\u5efa\u6a21\u5960\u5b9a\u57fa\u7840\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u5206\u6790\u6570\u636e\u7279\u5f81\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u5206\u6790\u6570\u636e\u7279\u5f81\u901a\u5e38\u6d89\u53ca\u4f7f\u7528Pandas\u5e93\u8fdb\u884c\u6570\u636e\u5904\u7406\u548c\u7279\u5f81\u63d0\u53d6\u3002\u60a8\u53ef\u4ee5\u901a\u8fc7describe()<\/code>\u65b9\u6cd5\u83b7\u53d6\u6570\u636e\u7684\u57fa\u672c\u7edf\u8ba1\u4fe1\u606f\uff0c\u5305\u62ec\u5747\u503c\u3001\u6807\u51c6\u5dee\u3001\u6700\u5c0f\u503c\u3001\u6700\u5927\u503c\u7b49\u3002\u6b64\u5916\uff0c\u4f7f\u7528info()<\/code>\u65b9\u6cd5\u53ef\u4ee5\u67e5\u770b\u6570\u636e\u7c7b\u578b\u548c\u7f3a\u5931\u503c\u7684\u60c5\u51b5\u3002\u7ed3\u5408\u53ef\u89c6\u5316\u5e93\u5982Matplotlib\u548cSeaborn\uff0c\u53ef\u4ee5\u5e2e\u52a9\u60a8\u66f4\u76f4\u89c2\u5730\u7406\u89e3\u6570\u636e\u7279\u5f81\u7684\u5206\u5e03\u548c\u5173\u7cfb\u3002<\/p>\n
\u6709\u54ea\u4e9bPython\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u7406\u89e3\u6570\u636e\u7279\u5f81\uff1f<\/strong>
\u5e38\u7528\u7684Python\u5e93\u5305\u62ecPandas\u3001NumPy\u548cScikit-learn\u3002Pandas\u662f\u6570\u636e\u5904\u7406\u7684\u6838\u5fc3\u5e93\uff0c\u53ef\u4ee5\u8f7b\u677e\u52a0\u8f7d\u548c\u64cd\u4f5c\u6570\u636e\u3002NumPy\u5219\u63d0\u4f9b\u4e86\u591a\u7ef4\u6570\u7ec4\u5bf9\u8c61\uff0c\u9002\u5408\u8fdb\u884c\u6570\u503c\u8ba1\u7b97\u3002\u800cScikit-learn\u5219\u4e13\u6ce8\u4e8e\u673a\u5668\u5b66\u4e60\uff0c\u63d0\u4f9b\u7279\u5f81\u9009\u62e9\u548c\u964d\u7ef4\u7b49\u5de5\u5177\uff0c\u8fd9\u4e9b\u90fd\u80fd\u5e2e\u52a9\u60a8\u66f4\u597d\u5730\u7406\u89e3\u6570\u636e\u7279\u5f81\u3002\u6b64\u5916\uff0cMatplotlib\u548cSeaborn\u53ef\u4ee5\u7528\u4e8e\u6570\u636e\u53ef\u89c6\u5316\uff0c\u5e2e\u52a9\u60a8\u8bc6\u522b\u7279\u5f81\u4e4b\u95f4\u7684\u5173\u7cfb\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u7f3a\u5931\u6570\u636e\u4ee5\u63d0\u9ad8\u7279\u5f81\u5206\u6790\u7684\u51c6\u786e\u6027\uff1f<\/strong>
\u5904\u7406\u7f3a\u5931\u6570\u636e\u662f\u7279\u5f81\u5206\u6790\u4e2d\u4e00\u4e2a\u91cd\u8981\u7684\u6b65\u9aa4\u3002\u60a8\u53ef\u4ee5\u9009\u62e9\u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c\u6216\u5217\uff0c\u6216\u8005\u4f7f\u7528\u63d2\u503c\u6cd5\u6216\u5747\u503c\/\u4e2d\u4f4d\u6570\u586b\u5145\u7f3a\u5931\u503c\u3002\u6b64\u5916\uff0c\u4f7f\u7528Pandas\u7684isnull()<\/code>\u548cfillna()<\/code>\u65b9\u6cd5\u53ef\u4ee5\u5e2e\u52a9\u60a8\u8bc6\u522b\u548c\u5904\u7406\u7f3a\u5931\u6570\u636e\u3002\u9488\u5bf9\u7279\u5f81\u9009\u62e9\uff0c\u60a8\u8fd8\u53ef\u4ee5\u8003\u8651\u4f7f\u7528Scikit-learn\u4e2d\u7684SimpleImputer<\/code>\uff0c\u4ee5\u66f4\u7cfb\u7edf\u7684\u65b9\u5f0f\u586b\u8865\u7f3a\u5931\u503c\uff0c\u4ece\u800c\u63d0\u9ad8\u540e\u7eed\u5206\u6790\u7684\u51c6\u786e\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u8981\u5728Python\u4e2d\u67e5\u770b\u6570\u636e\u7279\u5f81\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u3001NumPy\u3001scikit-learn\u7b49\u5e93\u3001Seaborn […]","protected":false},"author":3,"featured_media":1155770,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1155766"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1155766"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1155766\/revisions"}],"predecessor-version":[{"id":1155771,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1155766\/revisions\/1155771"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1155770"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1155766"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1155766"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1155766"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}