如何使用Sublime批量生成分析图表_自动绘图并保存为图片格式

pandas

matplotlib

seaborn

pip install pandas matplotlib seaborn

batch_plotter.py

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

def generate_and_save_plot(data_path, output_dir="plots", plot_type="line"):
    """
    根据数据文件生成图表并保存。
    :param data_path: CSV数据文件的路径。
    :param output_dir: 保存图表的目录。
    :param plot_type: 图表类型 ('line', 'bar', 'scatter' 等)。
    """
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)

    try:
        df = pd.read_csv(data_path)
    except Exception as e:
        print(f"Error reading {data_path}: {e}")
        return

    # 提取文件名作为图表名称前缀
    file_name = os.path.basename(data_path).replace('.csv', '')
    output_path = os.path.join(output_dir, f"{file_name}_{plot_type}.png")

    plt.figure(figsize=(10, 6)) # 设置图表大小

    if plot_type == "line":
        # 假设数据有'Date'和'Value'列
        if 'Date' in df.columns and 'Value' in df.columns:
            sns.lineplot(x='Date', y='Value', data=df)
            plt.title(f'{file_name} - Line Plot')
            plt.xlabel('Date')
            plt.ylabel('Value')
        else:
            print(f"Skipping line plot for {data_path}: 'Date' or 'Value' column missing.")
            plt.close()
            return
    elif plot_type == "bar":
        # 假设数据有'Category'和'Count'列
        if 'Category' in df.columns and 'Count' in df.columns:
            sns.barplot(x='Category', y='Count', data=df)
            plt.title(f'{file_name} - Bar Plot')
            plt.xlabel('Category')
            plt.ylabel('Count')
        else:
            print(f"Skipping bar plot for {data_path}: 'Category' or 'Count' column missing.")
            plt.close()
            return
    # 可以根据需要添加更多图表类型

    plt.tight_layout() # 自动调整布局，防止标签重叠
    plt.savefig(output_path)
    plt.close() # 关闭当前图表，释放内存
    print(f"Generated and saved: {output_path}")

if __name__ == "__main__":
    # 假设你的数据文件都放在 'data' 目录下
    data_folder = "data"
    output_folder = "generated_plots"

    if not os.path.exists(data_folder):
        print(f"Error: Data folder '{data_folder}' not found. Please create it and put your CSV files inside.")
    else:
        csv_files = [os.path.join(data_folder, f) for f in os.listdir(data_folder) if f.endswith('.csv')]

        if not csv_files:
            print(f"No CSV files found in '{data_folder}'.")
        else:
            print(f"Found {len(csv_files)} CSV files to process.")
            for csv_file in csv_files:
                # 为每个文件生成不同的图表类型，或者固定一种
                generate_and_save_plot(csv_file, output_folder, plot_type="line")
                # generate_and_save_plot(csv_file, output_folder, plot_type="bar") # 如果需要多种类型

batch_plotter.py

batch_plotter.py

data

sales_q1.csv

users_growth.csv

generated_plots

Tools > Build System > New Build System...

{
    "cmd": ["python", "$file"],
    "file_regex": "^[ ]*File \"(...*?)\", line ([0-9]*)",
    "selector": "source.python"
}

Python Plotter.sublime-build

batch_plotter.py

Tools > Build System > Python Plotter

Ctrl+B

Cmd+B

data

generated_plots

batch_plotter.py

if __name__ == "__main__":

# ... (前面的导入和函数定义不变) ...

if __name__ == "__main__":
    import argparse

    parser = argparse.ArgumentParser(description="Batch plot generator from CSV files.")
    parser.add_argument("--data_dir", type=str, default="data",
                        help="Directory containing CSV data files.")
    parser.add_argument("--output_dir", type=str, default="generated_plots",
                        help="Directory to save generated plots.")
    parser.add_argument("--plot_type", type=str, default="line",
                        help="Type of plot to generate (e.g., 'line', 'bar', 'scatter').")
    parser.add_argument("--file_pattern", type=str, default="*.csv",
                        help="Glob pattern for data files (e.g., 'sales_*.csv').")

    args = parser.parse_args()

    data_folder = args.data_dir
    output_folder = args.output_dir
    target_plot_type = args.plot_type
    file_pattern = args.file_pattern

    if not os.path.exists(data_folder):
        print(f"Error: Data folder '{data_folder}' not found. Please create it and put your CSV files inside.")
    else:
        # 使用glob模块来匹配文件模式
        import glob
        csv_files = glob.glob(os.path.join(data_folder, file_pattern))

        if not csv_files:
            print(f"No files matching '{file_pattern}' found in '{data_folder}'.")
        else:
            print(f"Found {len(csv_files)} files to process matching '{file_pattern}'.")
            for csv_file in csv_files:
                generate_and_save_plot(csv_file, output_folder, plot_type=target_plot_type)

python batch_plotter.py --data_dir my_sales_data --output_dir my_charts --plot_type bar --file_pattern "region_*.csv"

.sh

.bat