03-pandas-read&write-data.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "20115b65",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fdf016f6",
   "metadata": {},
   "source": [
    "> pandas提供了一些用于将表格型数据读取为DataFrame对象的函数。表6-1对它们进行了总结，其中read_csv和read_table可能会是你今后用得最多的。\n",
    "\n",
    "<img src=\"https://s2.loli.net/2022/06/20/1gnPhvBNakbAw2f.png\" alt=\"文件类型\" style=\"zoom: 67%;\" />"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2127941d",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "bda80ab8",
   "metadata": {},
   "outputs": [
    {
     "ename": "EmptyDataError",
     "evalue": "No columns to parse from file",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mStopIteration\u001b[0m                             Traceback (most recent call last)",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/python_parser.py:364\u001b[0m, in \u001b[0;36mPythonParser._infer_columns\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    363\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 364\u001b[0m     line \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_buffered_line\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    366\u001b[0m     \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mline_pos \u001b[38;5;241m<\u001b[39m\u001b[38;5;241m=\u001b[39m hr:\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/python_parser.py:596\u001b[0m, in \u001b[0;36mPythonParser._buffered_line\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    595\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 596\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_next_line\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/python_parser.py:696\u001b[0m, in \u001b[0;36mPythonParser._next_line\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    695\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 696\u001b[0m     orig_line \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_next_iter_line\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrow_num\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpos\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m    697\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpos \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/python_parser.py:760\u001b[0m, in \u001b[0;36mPythonParser._next_iter_line\u001b[0;34m(self, row_num)\u001b[0m\n\u001b[1;32m    759\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdata \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 760\u001b[0m line \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    761\u001b[0m \u001b[38;5;66;03m# for mypy\u001b[39;00m\n",
      "\u001b[0;31mStopIteration\u001b[0m: ",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[0;31mEmptyDataError\u001b[0m                            Traceback (most recent call last)",
      "Input \u001b[0;32mIn [9]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_clipboard\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m)\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/clipboards.py:85\u001b[0m, in \u001b[0;36mread_clipboard\u001b[0;34m(sep, **kwargs)\u001b[0m\n\u001b[1;32m     80\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(sep) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mengine\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mc\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m     81\u001b[0m     warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m     82\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mread_clipboard with regex separator does not work properly with c engine.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     83\u001b[0m     )\n\u001b[0;32m---> 85\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mStringIO\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msep\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/util/_decorators.py:311\u001b[0m, in \u001b[0;36mdeprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    305\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m>\u001b[39m num_allow_args:\n\u001b[1;32m    306\u001b[0m     warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m    307\u001b[0m         msg\u001b[38;5;241m.\u001b[39mformat(arguments\u001b[38;5;241m=\u001b[39marguments),\n\u001b[1;32m    308\u001b[0m         \u001b[38;5;167;01mFutureWarning\u001b[39;00m,\n\u001b[1;32m    309\u001b[0m         stacklevel\u001b[38;5;241m=\u001b[39mstacklevel,\n\u001b[1;32m    310\u001b[0m     )\n\u001b[0;32m--> 311\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py:680\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, error_bad_lines, warn_bad_lines, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options)\u001b[0m\n\u001b[1;32m    665\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m    666\u001b[0m     dialect,\n\u001b[1;32m    667\u001b[0m     delimiter,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    676\u001b[0m     defaults\u001b[38;5;241m=\u001b[39m{\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdelimiter\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m,\u001b[39m\u001b[38;5;124m\"\u001b[39m},\n\u001b[1;32m    677\u001b[0m )\n\u001b[1;32m    678\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m--> 680\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py:575\u001b[0m, in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m    572\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[1;32m    574\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[0;32m--> 575\u001b[0m parser \u001b[38;5;241m=\u001b[39m \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    577\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[1;32m    578\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py:933\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m    930\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m    932\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 933\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py:1235\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m   1232\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(msg)\n\u001b[1;32m   1234\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1235\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmapping\u001b[49m\u001b[43m[\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m]\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1236\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[1;32m   1237\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/python_parser.py:115\u001b[0m, in \u001b[0;36mPythonParser.__init__\u001b[0;34m(self, f, **kwds)\u001b[0m\n\u001b[1;32m    109\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_col_indices: \u001b[38;5;28mlist\u001b[39m[\u001b[38;5;28mint\u001b[39m] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    110\u001b[0m columns: \u001b[38;5;28mlist\u001b[39m[\u001b[38;5;28mlist\u001b[39m[Scalar \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m]]\n\u001b[1;32m    111\u001b[0m (\n\u001b[1;32m    112\u001b[0m     columns,\n\u001b[1;32m    113\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnum_original_columns,\n\u001b[1;32m    114\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39munnamed_cols,\n\u001b[0;32m--> 115\u001b[0m ) \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_infer_columns\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    117\u001b[0m \u001b[38;5;66;03m# Now self.columns has the set of columns that we will process.\u001b[39;00m\n\u001b[1;32m    118\u001b[0m \u001b[38;5;66;03m# The original set is stored in self.original_columns.\u001b[39;00m\n\u001b[1;32m    119\u001b[0m \u001b[38;5;66;03m# error: Cannot determine type of 'index_names'\u001b[39;00m\n\u001b[1;32m    120\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns: \u001b[38;5;28mlist\u001b[39m[Hashable]\n",
      "File \u001b[0;32m/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/python_parser.py:386\u001b[0m, in \u001b[0;36mPythonParser._infer_columns\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    383\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m columns, num_original_columns, unnamed_cols\n\u001b[1;32m    385\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnames:\n\u001b[0;32m--> 386\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m EmptyDataError(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo columns to parse from file\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n\u001b[1;32m    388\u001b[0m     line \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnames[:]\n\u001b[1;32m    390\u001b[0m this_columns: \u001b[38;5;28mlist\u001b[39m[Scalar \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m] \u001b[38;5;241m=\u001b[39m []\n",
      "\u001b[0;31mEmptyDataError\u001b[0m: No columns to parse from file"
     ]
    }
   ],
   "source": [
    "print(pd.read_clipboard())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9fd6f9f3",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bdf8e9e0",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7349c3a0",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}