Pandas文件处理中read_csv和to_csv参数详解与实战指南

import pandas as pd

# 读取CSV文件
df = pd.read_csv('example.csv')

# 打印数据框的前几行
print(df.head())

import pandas as pd

# 读取txt文件，指定分隔符为制表符
df_txt = pd.read_csv('example.txt', sep='\t')

# 打印数据框的前几行
print(df_txt.head())

import pandas as pd

# 创建一个数据框
data = {'Name': ['Alice', 'Bob', 'Charlie'],
        'Age': [25, 30, 35],
        'City': ['New York', 'San Francisco', 'Los Angeles']}

df_new = pd.DataFrame(data)

# 将数据框写入CSV文件
df_new.to_csv('new_example.csv', index=False)

import pandas as pd

# 读取CSV文件，指定编码和解析日期
df_advanced = pd.read_csv('advanced_example.csv', encoding='utf-8', parse_dates=['Date'])

# 打印数据框的前几行
print(df_advanced.head())

import pandas as pd

# 创建一个包含日期的数据框
data_advanced = {'Name': ['Alice', 'Bob', 'Charlie'],
                 'Age': [25, 30, 35],
                 'Date': pd.to_datetime(['2022-01-01', '2022-02-01', '2022-03-01'])}

df_advanced = pd.DataFrame(data_advanced)

# 将数据框写入CSV文件，指定日期格式和压缩格式
df_advanced.to_csv('advanced_example.csv', index=False, date_format='%Y-%m-%d', compression='gzip')

import pandas as pd

# 读取CSV文件，指定缺失值为-1
df_missing = pd.read_csv('missing_example.csv', na_values=-1)

# 删除包含缺失值的行
df_missing_cleaned = df_missing.dropna()

# 打印清理后的数据框
print(df_missing_cleaned)

import pandas as pd

# 读取CSV文件
df_dirty = pd.read_csv('dirty_example.csv')

# 使用query方法进行数据过滤
df_cleaned = df_dirty.query('Age > 0')

# 使用replace方法替换特定值
df_cleaned['City'].replace({'NYC': 'New York City'}, inplace=True)

# 打印清理后的数据框
print(df_cleaned)

import pandas as pd
import logging

# 设置日志记录
logging.basicConfig(filename='data_processing.log', level=logging.ERROR)

try:
    # 尝试读取CSV文件
    df = pd.read_csv('nonexistent_file.csv')

except FileNotFoundError as e:
    # 处理文件不存在的异常
    logging.error(f'File not found: {e}')

except pd.errors.ParserError as e:
    # 处理文件格式错误的异常
    logging.error(f'Error parsing file: {e}')

else:
    # 如果没有异常，执行正常的数据处理操作
    print(df.head())

import pandas as pd

# 读取CSV文件
df_analysis = pd.read_csv('analysis_example.csv')

# 输出数据集的统计信息
print(df_analysis.describe())

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# 读取CSV文件
df_visualization = pd.read_csv('visualization_example.csv')

# 绘制散点图
sns.scatterplot(x='Age', y='Income', data=df_visualization)
plt.title('Scatter Plot of Age vs Income')
plt.show()

import pandas as pd

# 读取大规模CSV文件，指定分块大小
chunk_size = 10000
df_large = pd.read_csv('large_example.csv', chunksize=chunk_size)

# 逐块处理数据
for chunk in df_large:
    # 进行数据处理操作
    process_chunk(chunk)

import pandas as pd

# 读取包含日期列的CSV文件，进行日期解析和设置索引
df_time_series = pd.read_csv('time_series_example.csv', parse_dates=['Date'], index_col='Date')

# 打印数据框的前几行
print(df_time_series.head())

import pandas as pd

# 生成一个包含日期范围的时间序列数据框
date_range = pd.date_range(start='2022-01-01', end='2022-01-10', freq='D')
df_time_range = pd.DataFrame({'Value': range(1, 11)}, index=date_range)

# 打印数据框
print(df_time_range)

import pandas as pd

# 读取包含日期列的CSV文件，进行日期解析和设置索引
df_resample = pd.read_csv('time_series_example.csv', parse_dates=['Date'], index_col='Date')

# 按月重采样，计算均值
df_monthly_mean = df_resample['Value'].resample('M').mean()

# 使用滚动窗口计算移动平均值
df_rolling_mean = df_resample['Value'].rolling(window=3).mean()

# 打印结果
print(df_monthly_mean)
print(df_rolling_mean)

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# 读取CSV文件
df_ml = pd.read_csv('machine_learning_example.csv')

# 分割数据集为训练集和测试集
X = df_ml.drop('Label', axis=1)
y = df_ml['Label']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 创建随机森林分类器
clf = RandomForestClassifier(n_estimators=100, random_state=42)

# 训练模型
clf.fit(X_train, y_train)

# 预测并评估模型
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)

# 打印准确率
print(f'Model Accuracy: {accuracy}')