{"id":1182382,"date":"2025-01-15T19:02:32","date_gmt":"2025-01-15T11:02:32","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1182382.html"},"modified":"2025-01-15T19:02:34","modified_gmt":"2025-01-15T11:02:34","slug":"python%e5%a6%82%e4%bd%95%e8%af%bb%e5%8f%96csv%e7%9a%84%e5%88%97","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1182382.html","title":{"rendered":"python\u5982\u4f55\u8bfb\u53d6csv\u7684\u5217"},"content":{"rendered":"

\"python\u5982\u4f55\u8bfb\u53d6csv\u7684\u5217\"<\/p>\n

Python\u8bfb\u53d6CSV\u7684\u5217\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528\u5185\u7f6ecsv\u6a21\u5757\u3001\u4f7f\u7528pandas\u5e93\u3001\u4f7f\u7528numpy\u5e93\u3002<\/strong>\u4e0b\u9762\u5c06\u8be6\u7ec6\u63cf\u8ff0\u8fd9\u4e09\u79cd\u65b9\u6cd5\uff0c\u5e76\u7740\u91cd\u4ecb\u7ecdpandas\u5e93\u7684\u4f7f\u7528\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528\u5185\u7f6ecsv\u6a21\u5757<\/h3>\n<\/p>\n

Python\u5185\u7f6e\u7684csv\u6a21\u5757\u63d0\u4f9b\u4e86\u65b9\u4fbf\u7684CSV\u6587\u4ef6\u8bfb\u5199\u529f\u80fd\u3002\u4ee5\u4e0b\u662f\u5982\u4f55\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7279\u5b9a\u5217\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n

import csv<\/p>\n
filename = "example.csv"<\/p>\n
column_name = "desired_column"<\/p>\n
with open(filename, mode='r', newline='') as file:<\/p>\n
    reader = csv.DictReader(file)<\/p>\n
    column_data = [row[column_name] for row in reader]<\/p>\n
print(column_data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u9996\u5148\u5bfc\u5165csv\u6a21\u5757\uff0c\u7136\u540e\u6253\u5f00CSV\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528csv.DictReader<\/code>\u5c06\u6bcf\u4e00\u884c\u89e3\u6790\u4e3a\u5b57\u5178\u3002\u901a\u8fc7\u5217\u8868\u63a8\u5bfc\u5f0f\u63d0\u53d6\u6240\u9700\u5217\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528pandas\u5e93<\/h3>\n<\/p>\n
Pandas\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u548c\u5206\u6790\u5e93\uff0c\u7279\u522b\u9002\u5408\u5904\u7406\u8868\u683c\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u5982\u4f55\u4f7f\u7528pandas\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7279\u5b9a\u5217\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
filename = "example.csv"<\/p>\n
column_name = "desired_column"<\/p>\n
df = pd.read_csv(filename)<\/p>\n
column_data = df[column_name].tolist()<\/p>\n
print(column_data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528pandas\u7684\u4f18\u52bf\u5728\u4e8e\u5176\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u80fd\u529b\u548c\u7b80\u6d01\u7684\u8bed\u6cd5\u3002<\/strong>\u4f8b\u5982\uff0cpandas\u4e0d\u4ec5\u53ef\u4ee5\u8f7b\u677e\u8bfb\u53d6\u6307\u5b9a\u5217\uff0c\u8fd8\u53ef\u4ee5\u8fdb\u884c\u6570\u636e\u7b5b\u9009\u3001\u6570\u636e\u7edf\u8ba1\u7b49\u64cd\u4f5c\u3002\u4ee5\u4e0b\u662f\u66f4\u8be6\u7ec6\u7684\u4ecb\u7ecd\uff1a<\/p>\n<\/p>\n
1. \u8bfb\u53d6\u591a\u4e2a\u5217<\/h4>\n<\/p>\n
\u5982\u679c\u9700\u8981\u8bfb\u53d6\u591a\u4e2a\u5217\uff0c\u53ef\u4ee5\u5728read_csv<\/code>\u65b9\u6cd5\u4e2d\u6307\u5b9ausecols<\/code>\u53c2\u6570\uff1a<\/p>\n<\/p>\n
columns_to_read = ["column1", "column2"]<\/p>\n
df = pd.read_csv(filename, usecols=columns_to_read)<\/p>\n
print(df)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u6570\u636e\u7b5b\u9009\u548c\u5904\u7406<\/h4>\n<\/p>\n
\u8bfb\u53d6\u6570\u636e\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u63d0\u4f9b\u7684\u5404\u79cd\u65b9\u6cd5\u5bf9\u6570\u636e\u8fdb\u884c\u5904\u7406\u3002\u4f8b\u5982\uff0c\u7b5b\u9009\u6570\u636e\u3001\u8ba1\u7b97\u7edf\u8ba1\u91cf\u7b49\u3002<\/p>\n<\/p>\n
# \u7b5b\u9009\u6570\u636e<\/p>\n
filtered_df = df[df['column1'] > 10]<\/p>\n
\u8ba1\u7b97\u7edf\u8ba1\u91cf<\/strong><\/h2>\n
mean_value = df['column1'].mean()<\/p>\n
print(mean_value)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528numpy\u5e93<\/h3>\n<\/p>\n
Numpy\u662f\u4e00\u4e2a\u7528\u4e8e\u79d1\u5b66\u8ba1\u7b97\u7684\u5e93\uff0c\u7279\u522b\u64c5\u957f\u5904\u7406\u6570\u503c\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u5982\u4f55\u4f7f\u7528numpy\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7279\u5b9a\u5217\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import numpy as np<\/p>\n
filename = "example.csv"<\/p>\n
column_index = 1  # \u5047\u8bbe\u6211\u4eec\u8981\u8bfb\u53d6\u7b2c\u4e8c\u5217<\/p>\n
data = np.genfromtxt(filename, delimiter=',', skip_header=1, usecols=column_index)<\/p>\n
print(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
numpy\u7684genfromtxt<\/code>\u51fd\u6570\u7528\u4e8e\u4ece\u6587\u672c\u6587\u4ef6\u4e2d\u751f\u6210\u6570\u636e\u6570\u7ec4\u3002\u901a\u8fc7\u6307\u5b9ausecols<\/code>\u53c2\u6570\u53ef\u4ee5\u8bfb\u53d6\u7279\u5b9a\u5217\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
\u56db\u3001\u7efc\u5408\u6bd4\u8f83\u4e0e\u5efa\u8bae<\/h3>\n<\/p>\n
1. \u5185\u7f6ecsv\u6a21\u5757<\/h4>\n<\/p>\n
\u4f18\u70b9\uff1a<\/strong> \u8f7b\u91cf\u7ea7\u3001\u65e0\u9700\u989d\u5916\u5b89\u88c5\u5e93\u3002<\/p>\n
\u7f3a\u70b9\uff1a<\/strong> \u529f\u80fd\u8f83\u4e3a\u57fa\u7840\uff0c\u5904\u7406\u5927\u578b\u6570\u636e\u6216\u590d\u6742\u64cd\u4f5c\u65f6\u4e0d\u591f\u4fbf\u5229\u3002<\/p>\n<\/p>\n
2. Pandas\u5e93<\/h4>\n<\/p>\n
\u4f18\u70b9\uff1a<\/strong> \u529f\u80fd\u5f3a\u5927\u3001\u8bed\u6cd5\u7b80\u6d01\u3001\u9002\u5408\u5904\u7406\u590d\u6742\u6570\u636e\u64cd\u4f5c\u3002<\/p>\n
\u7f3a\u70b9\uff1a<\/strong> \u5bf9\u4e8e\u7b80\u5355\u4efb\u52a1\u53ef\u80fd\u663e\u5f97\u8fc7\u4e8e\u91cd\u91cf\u7ea7\u3002<\/p>\n<\/p>\n
3. Numpy\u5e93<\/h4>\n<\/p>\n
\u4f18\u70b9\uff1a<\/strong> \u9ad8\u6548\u5904\u7406\u6570\u503c\u6570\u636e\u3001\u9002\u5408\u79d1\u5b66\u8ba1\u7b97\u3002<\/p>\n
\u7f3a\u70b9\uff1a<\/strong> \u5bf9\u4e8e\u975e\u6570\u503c\u6570\u636e\u5904\u7406\u80fd\u529b\u6709\u9650\u3002<\/p>\n<\/p>\n
\u7efc\u5408\u8003\u8651\uff0c\u5982\u679c\u53ea\u662f\u7b80\u5355\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u5217\u6570\u636e\uff0c\u4e14\u4e0d\u6d89\u53ca\u590d\u6742\u64cd\u4f5c\uff0c\u53ef\u4ee5\u9009\u62e9\u5185\u7f6ecsv\u6a21\u5757\u3002\u5982\u679c\u9700\u8981\u8fdb\u884c\u590d\u6742\u7684\u6570\u636e\u5206\u6790\u548c\u5904\u7406\uff0c\u5efa\u8bae\u4f7f\u7528pandas\u3002\u5bf9\u4e8e\u6570\u503c\u8ba1\u7b97\u5bc6\u96c6\u7684\u4efb\u52a1\uff0cnumpy\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u9009\u62e9\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u5217\u2014\u2014\u66f4\u6df1\u5165\u7684\u4f7f\u7528\u793a\u4f8b<\/h3>\n<\/p>\n
1. \u4f7f\u7528\u5185\u7f6ecsv\u6a21\u5757\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u5217<\/h4>\n<\/p>\n
\u8ba9\u6211\u4eec\u66f4\u8be6\u7ec6\u5730\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528\u5185\u7f6ecsv\u6a21\u5757\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u5217\u3002<\/p>\n<\/p>\n
import csv<\/p>\n
def read_csv_column(filename, column_name):<\/p>\n
    with open(filename, mode='r', newline='') as file:<\/p>\n
        reader = csv.DictReader(file)<\/p>\n
        column_data = [row[column_name] for row in reader]<\/p>\n
    return column_data<\/p>\n
\u793a\u4f8b\u4f7f\u7528<\/strong><\/h2>\n
filename = "example.csv"<\/p>\n
column_name = "desired_column"<\/p>\n
data = read_csv_column(filename, column_name)<\/p>\n
print(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u51fd\u6570read_csv_column<\/code>\u63a5\u53d7\u6587\u4ef6\u540d\u548c\u5217\u540d\u4f5c\u4e3a\u53c2\u6570\uff0c\u8fd4\u56de\u8be5\u5217\u7684\u6570\u636e\u3002\u8fd9\u4e2a\u51fd\u6570\u53ef\u4ee5\u65b9\u4fbf\u5730\u91cd\u590d\u4f7f\u7528\u3002<\/p>\n<\/p>\n
2. \u4f7f\u7528pandas\u5e93\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u5217<\/h4>\n<\/p>\n
Pandas\u5e93\u63d0\u4f9b\u4e86\u66f4\u591a\u7684\u529f\u80fd\uff0c\u4f7f\u5f97\u5904\u7406CSV\u6587\u4ef6\u66f4\u52a0\u9ad8\u6548\u548c\u4fbf\u6377\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u66f4\u8be6\u7ec6\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
def read_csv_column(filename, column_name):<\/p>\n
    df = pd.read_csv(filename)<\/p>\n
    return df[column_name].tolist()<\/p>\n
def read_multiple_columns(filename, columns):<\/p>\n
    df = pd.read_csv(filename, usecols=columns)<\/p>\n
    return df<\/p>\n
def filter_data(df, column_name, threshold):<\/p>\n
    return df[df[column_name] > threshold]<\/p>\n
def calculate_statistics(df, column_name):<\/p>\n
    return {<\/p>\n
        "mean": df[column_name].mean(),<\/p>\n
        "median": df[column_name].median(),<\/p>\n
        "std": df[column_name].std()<\/p>\n
    }<\/p>\n
\u793a\u4f8b\u4f7f\u7528<\/strong><\/h2>\n
filename = "example.csv"<\/p>\n
column_name = "desired_column"<\/p>\n
columns = ["column1", "column2"]<\/p>\n
\u8bfb\u53d6\u5355\u5217\u6570\u636e<\/strong><\/h2>\n
data = read_csv_column(filename, column_name)<\/p>\n
print(data)<\/p>\n
\u8bfb\u53d6\u591a\u5217\u6570\u636e<\/strong><\/h2>\n
df = read_multiple_columns(filename, columns)<\/p>\n
print(df)<\/p>\n
\u7b5b\u9009\u6570\u636e<\/strong><\/h2>\n
filtered_df = filter_data(df, "column1", 10)<\/p>\n
print(filtered_df)<\/p>\n
\u8ba1\u7b97\u7edf\u8ba1\u91cf<\/strong><\/h2>\n
stats = calculate_statistics(df, "column1")<\/p>\n
print(stats)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528pandas\u5e93\u8fdb\u884c\u591a\u79cd\u6570\u636e\u5904\u7406\u64cd\u4f5c\uff0c\u5305\u62ec\u8bfb\u53d6\u5355\u5217\u3001\u591a\u5217\u3001\u7b5b\u9009\u6570\u636e\u548c\u8ba1\u7b97\u7edf\u8ba1\u91cf\u3002<\/p>\n<\/p>\n
3. \u4f7f\u7528numpy\u5e93\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u5217<\/h4>\n<\/p>\n
Numpy\u5e93\u867d\u7136\u4e3b\u8981\u7528\u4e8e\u6570\u503c\u8ba1\u7b97\uff0c\u4f46\u4e5f\u53ef\u4ee5\u8bfb\u53d6CSV\u6587\u4ef6\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u8be6\u7ec6\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import numpy as np<\/p>\n
def read_csv_column(filename, column_index):<\/p>\n
    data = np.genfromtxt(filename, delimiter=',', skip_header=1, usecols=column_index)<\/p>\n
    return data<\/p>\n
def calculate_statistics(data):<\/p>\n
    return {<\/p>\n
        "mean": np.mean(data),<\/p>\n
        "median": np.median(data),<\/p>\n
        "std": np.std(data)<\/p>\n
    }<\/p>\n
\u793a\u4f8b\u4f7f\u7528<\/strong><\/h2>\n
filename = "example.csv"<\/p>\n
column_index = 1  # \u5047\u8bbe\u6211\u4eec\u8981\u8bfb\u53d6\u7b2c\u4e8c\u5217<\/p>\n
\u8bfb\u53d6\u5217\u6570\u636e<\/strong><\/h2>\n
data = read_csv_column(filename, column_index)<\/p>\n
print(data)<\/p>\n
\u8ba1\u7b97\u7edf\u8ba1\u91cf<\/strong><\/h2>\n
stats = calculate_statistics(data)<\/p>\n
print(stats)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u4e2a\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528numpy\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u5217\uff0c\u5e76\u8ba1\u7b97\u8be5\u5217\u7684\u7edf\u8ba1\u91cf\u3002<\/p>\n<\/p>\n
\u516d\u3001\u5b9e\u9645\u5e94\u7528\u4e2d\u7684\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n
1. \u6587\u4ef6\u7f16\u7801\u95ee\u9898<\/h4>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0cCSV\u6587\u4ef6\u53ef\u80fd\u4f7f\u7528\u4e0d\u540c\u7684\u7f16\u7801\u683c\u5f0f\u3002\u8bfb\u53d6\u6587\u4ef6\u65f6\u9700\u8981\u6ce8\u610f\u7f16\u7801\u95ee\u9898\uff0c\u5426\u5219\u53ef\u80fd\u5bfc\u81f4\u8bfb\u53d6\u5931\u8d25\u6216\u6570\u636e\u9519\u8bef\u3002\u53ef\u4ee5\u901a\u8fc7\u6307\u5b9a\u7f16\u7801\u53c2\u6570\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
df = pd.read_csv("example.csv", encoding='utf-8')<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u7f3a\u5931\u503c\u5904\u7406<\/h4>\n<\/p>\n
\u5728\u5b9e\u9645\u6570\u636e\u5904\u7406\u4e2d\uff0cCSV\u6587\u4ef6\u4e2d\u53ef\u80fd\u5305\u542b\u7f3a\u5931\u503c\u3002\u5904\u7406\u7f3a\u5931\u503c\u662f\u6570\u636e\u6e05\u6d17\u7684\u91cd\u8981\u6b65\u9aa4\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528pandas\u5904\u7406\u7f3a\u5931\u503c\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
df = pd.read_csv("example.csv")<\/p>\n
\u67e5\u770b\u7f3a\u5931\u503c\u60c5\u51b5<\/strong><\/h2>\n
print(df.isnull().sum())<\/p>\n
\u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c<\/strong><\/h2>\n
df_cleaned = df.dropna()<\/p>\n
\u7528\u6307\u5b9a\u503c\u586b\u5145\u7f3a\u5931\u503c<\/strong><\/h2>\n
df_filled = df.fillna(0)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u5927\u6587\u4ef6\u5904\u7406<\/h4>\n<\/p>\n
\u5f53CSV\u6587\u4ef6\u975e\u5e38\u5927\u65f6\uff0c\u53ef\u80fd\u4f1a\u5bfc\u81f4\u5185\u5b58\u4e0d\u8db3\u7684\u95ee\u9898\u3002\u53ef\u4ee5\u4f7f\u7528\u5206\u5757\u8bfb\u53d6\u7684\u65b9\u6cd5\u5904\u7406\u5927\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
chunksize = 10000  # \u6bcf\u6b21\u8bfb\u53d610000\u884c<\/p>\n
for chunk in pd.read_csv("large_example.csv", chunksize=chunksize):<\/p>\n
    # \u5bf9\u6bcf\u4e2a\u5757\u8fdb\u884c\u5904\u7406<\/p>\n
    print(chunk.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u5728Python\u4e2d\u8bfb\u53d6CSV\u6587\u4ef6\u7684\u5217\u4e3b\u8981\u6709\u4e09\u79cd\u65b9\u6cd5\uff1a\u4f7f\u7528\u5185\u7f6ecsv\u6a21\u5757\u3001\u4f7f\u7528pandas\u5e93\u548c\u4f7f\u7528numpy\u5e93\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u4f18\u7f3a\u70b9\uff0c\u9009\u62e9\u54ea\u79cd\u65b9\u6cd5\u53d6\u51b3\u4e8e\u5177\u4f53\u7684\u9700\u6c42\u548c\u5e94\u7528\u573a\u666f\u3002<\/p>\n<\/p>\n
    \n
  1. \u5185\u7f6ecsv\u6a21\u5757<\/strong>\uff1a\u9002\u5408\u5904\u7406\u7b80\u5355\u7684CSV\u6587\u4ef6\u64cd\u4f5c\uff0c\u4f18\u70b9\u662f\u8f7b\u91cf\u7ea7\uff0c\u65e0\u9700\u989d\u5916\u5b89\u88c5\u5e93\uff0c\u4f46\u529f\u80fd\u8f83\u4e3a\u57fa\u7840\u3002<\/li>\n
  2. pandas\u5e93<\/strong>\uff1a\u529f\u80fd\u5f3a\u5927\uff0c\u9002\u5408\u5904\u7406\u590d\u6742\u7684\u6570\u636e\u5206\u6790\u548c\u5904\u7406\u4efb\u52a1\uff0c\u8bed\u6cd5\u7b80\u6d01\uff0c\u4f46\u5bf9\u7b80\u5355\u4efb\u52a1\u53ef\u80fd\u663e\u5f97\u8fc7\u4e8e\u91cd\u91cf\u7ea7\u3002<\/li>\n
  3. numpy\u5e93<\/strong>\uff1a\u9ad8\u6548\u5904\u7406\u6570\u503c\u6570\u636e\uff0c\u9002\u5408\u79d1\u5b66\u8ba1\u7b97\uff0c\u4f46\u5bf9\u975e\u6570\u503c\u6570\u636e\u5904\u7406\u80fd\u529b\u6709\u9650\u3002<\/li>\n<\/ol>\n
    \u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u8fd8\u9700\u8981\u6ce8\u610f\u6587\u4ef6\u7f16\u7801\u3001\u7f3a\u5931\u503c\u5904\u7406\u548c\u5927\u6587\u4ef6\u5904\u7406\u7b49\u95ee\u9898\uff0c\u4ee5\u786e\u4fdd\u6570\u636e\u8bfb\u53d6\u548c\u5904\u7406\u7684\u6b63\u786e\u6027\u548c\u9ad8\u6548\u6027\u3002<\/p>\n<\/p>\n
    \u901a\u8fc7\u4e0a\u8ff0\u8be6\u7ec6\u4ecb\u7ecd\uff0c\u76f8\u4fe1\u60a8\u5df2\u7ecf\u5bf9\u5982\u4f55\u4f7f\u7528Python\u8bfb\u53d6CSV\u6587\u4ef6\u7684\u5217\u6709\u4e86\u6df1\u5165\u7684\u4e86\u89e3\u548c\u638c\u63e1\u3002\u5e0c\u671b\u8fd9\u4e9b\u5185\u5bb9\u5bf9\u60a8\u7684\u5de5\u4f5c\u548c\u5b66\u4e60\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n
    \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
     \u5982\u4f55\u4f7f\u7528Python\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u7279\u5b9a\u5217\uff1f<\/strong>
    \u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u5e93\u8f7b\u677e\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u7279\u5b9a\u5217\u3002\u9996\u5148\uff0c\u786e\u4fdd\u4f60\u5df2\u7ecf\u5b89\u88c5\u4e86pandas\u5e93\u3002\u4f7f\u7528pd.read_csv()<\/code>\u51fd\u6570\u8bfb\u53d6CSV\u6587\u4ef6\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4f20\u5165usecols<\/code>\u53c2\u6570\u6765\u6307\u5b9a\u9700\u8981\u8bfb\u53d6\u7684\u5217\u3002\u4f8b\u5982\uff1a  <\/p>\n
    import pandas as pd\ndata = pd.read_csv('file.csv', usecols=['column_name'])\n<\/code><\/pre>\n
    \u8fd9\u6837\u5c31\u53ef\u4ee5\u53ea\u8bfb\u53d6\u6307\u5b9a\u7684\u5217\u4e86\u3002<\/p>\n
    \u5728\u8bfb\u53d6CSV\u65f6\uff0c\u5982\u4f55\u5904\u7406\u7f3a\u5931\u503c\uff1f<\/strong>
    \u5728\u4f7f\u7528pandas\u8bfb\u53d6CSV\u6587\u4ef6\u65f6\uff0c\u7f3a\u5931\u503c\u4f1a\u81ea\u52a8\u88ab\u8bc6\u522b\u3002\u4f60\u53ef\u4ee5\u5728\u52a0\u8f7d\u6570\u636e\u65f6\u4f7f\u7528na_values<\/code>\u53c2\u6570\u6765\u6307\u5b9a\u54ea\u4e9b\u503c\u5e94\u88ab\u89c6\u4e3a\u7f3a\u5931\u503c\u3002\u6b64\u5916\uff0c\u4f7f\u7528fillna()<\/code>\u51fd\u6570\u53ef\u4ee5\u586b\u5145\u7f3a\u5931\u503c\uff0c\u6216\u8005\u4f7f\u7528dropna()<\/code>\u51fd\u6570\u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c\u3002\u4f8b\u5982\uff1a  <\/p>\n
    data = pd.read_csv('file.csv', na_values=['', 'NA'])\ndata.fillna(0, inplace=True)  # \u5c06\u7f3a\u5931\u503c\u586b\u5145\u4e3a0\n<\/code><\/pre>\n
    \u662f\u5426\u53ef\u4ee5\u4f7f\u7528Python\u5185\u7f6e\u6a21\u5757\u8bfb\u53d6CSV\u6587\u4ef6\u7684\u5217\uff1f<\/strong>
    \u786e\u5b9e\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5185\u7f6ecsv\u6a21\u5757\u6765\u8bfb\u53d6CSV\u6587\u4ef6\u3002\u901a\u8fc7csv.reader<\/code>\u53ef\u4ee5\u9010\u884c\u8bfb\u53d6\u6587\u4ef6\uff0c\u5e76\u63d0\u53d6\u7279\u5b9a\u5217\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a  <\/p>\n
    import csv\nwith open('file.csv', mode='r') as file:\n    reader = csv.reader(file)\n    for row in reader:\n        print(row[column_index])  # column_index\u4e3a\u4f60\u60f3\u8bfb\u53d6\u7684\u5217\u7d22\u5f15\n<\/code><\/pre>\n
    \u6b64\u65b9\u6cd5\u63d0\u4f9b\u4e86\u66f4\u5e95\u5c42\u7684\u63a7\u5236\uff0c\u4f46\u76f8\u6bd4\u4e8epandas\u5904\u7406\u8d77\u6765\u76f8\u5bf9\u7e41\u7410\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u8bfb\u53d6CSV\u7684\u5217\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528\u5185\u7f6ecsv\u6a21\u5757\u3001\u4f7f\u7528pandas\u5e93\u3001\u4f7f\u7528numpy\u5e93\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u63cf\u8ff0 […]","protected":false},"author":3,"featured_media":1182389,"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\/1182382"}],"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=1182382"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1182382\/revisions"}],"predecessor-version":[{"id":1182391,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1182382\/revisions\/1182391"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1182389"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1182382"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1182382"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1182382"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}