digisam - How many pages in the year 1666?.ipynb

digisam - How many pages for the year 1666?.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": false
      },
      "id": "d8aa77b1",
      "cell_type": "code",
      "source": "import pandas as pd\n\npd.set_option(\"display.max_rows\", None)",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "id": "95a0d080",
      "cell_type": "code",
      "source": "mods_info_df = pd.read_csv(\"/home/mike/devel/qurator-data/digisam/mods_info/mods_info_df_all.2023-01-23.csv\",\n                          index_col=0)",
      "execution_count": 2,
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": "/tmp/ipykernel_35645/4200959452.py:1: DtypeWarning: Columns (29,32,73,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,210,211,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284,285,286,287,288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,340,341,342,343,344,345,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,378,379,380,381,382,383,384,385,386,387,388,389,390,391,392,393,394,395,396,397,398,399,400,401,402,403,404,405,406,407,408,409,410,411,412,413,414,415,416,417,418,419,420,421,422,423,424,425,426,427,428,429,430,431,432,433,434,435,436) have mixed types. Specify dtype option on import or set low_memory=False.\n  mods_info_df = pd.read_csv(\"/home/mike/devel/qurator-data/digisam/mods_info/mods_info_df_all.2023-01-23.csv\",\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "id": "09f08dc8",
      "cell_type": "code",
      "source": "# Select works from 1666 (created or published)\nmods_info_df = mods_info_df[\n    mods_info_df[\"originInfo-production0_dateCreated\"].astype(\"string\").str.startswith(\"1666\") |\n    mods_info_df[\"originInfo-publication0_dateIssued\"].astype(\"string\").str.startswith(\"1666\")\n]",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "id": "1bd72d63",
      "cell_type": "code",
      "source": "# Page count could be done by looking at the count of files in the PRESENTATION METS file group.\n# This is only slightly incorrect as it also contains e.g. the color checker, but probably suffices in this case.\n#\n# (Just printing a few of the >300 values here)\nmods_info_df[\"mets_fileSec_fileGrp-PRESENTATION-count\"].head()",
      "execution_count": 4,
      "outputs": [
        {
          "data": {
            "text/plain": "PPN607617047    33.0\nPPN848333268    20.0\nPPN873829409    17.0\nPPN664526918    12.0\nPPN71528990X    21.0\nName: mets_fileSec_fileGrp-PRESENTATION-count, dtype: float64"
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "id": "6e4cc65e",
      "cell_type": "code",
      "source": "# Summing it up:\n\nmods_info_df[\"mets_fileSec_fileGrp-PRESENTATION-count\"].sum()",
      "execution_count": 5,
      "outputs": [
        {
          "data": {
            "text/plain": "55309.0"
          },
          "execution_count": 5,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    }
  ],
  "metadata": {
    "gist": {
      "id": "",
      "data": {
        "description": "digisam - How many pages in the year 1666?.ipynb",
        "public": false
      }
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3 (ipykernel)",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.9.13",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "toc": {
      "nav_menu": {},
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "base_numbering": 1,
      "title_cell": "Table of Contents",
      "title_sidebar": "Contents",
      "toc_cell": false,
      "toc_position": {},
      "toc_section_display": true,
      "toc_window_display": true
    },
    "hide_input": false
  },
  "nbformat": 4,
  "nbformat_minor": 5
}