Landing branch

.gitignore

@@ -1,3 +1,10 @@
+#Data files 
+*.csv
+*.json
+*.ndjson
+*.db
+
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -191,4 +198,9 @@ cython_debug/
 #  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
 #  refer to https://docs.cursor.com/context/ignore-files
 .cursorignore
-.cursorindexingignore
+.cursorindexingignore
+
+# Dataset files
+*.csv
+*.json
+*.ndjson

Library.ipynb

@@ -0,0 +1,36 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d3799054-696c-48ee-b1db-d95976e59a30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "df = pd.read_csv(\"credits.csv, \"keywords.csv\", \"links_small.csv\", \"links.csv\", )"
+   ]
+  }
+ ],
+ "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": "3.14.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

README.md

@@ -1,48 +1,2 @@
-# Shhhh! CentralLibraryData
 
-the place CentralLibrary gets its content from.
 
-As a team, fork this repository to an Organization and submit the URL of your fork via the Student Portal. Each teammate will submit the **SAME URL.** 
-
-There are things you _need to know_ and ask Instructors about. What are they? When can we schedule some dialog sessions so that you can get some ideas about what to study? 
-
-Group Work requires that y'all think about plans, and priorities, and schedule some time to get to experts and senior devs to ask intelligent questions, and learn important topics. 
-
-_What are they?_
-
-## Project Overview
-
-Build a series of pipelines that feed the content needed by a comprehensive Library Management System built by the Java group.
-
-This is a Data project matched to the Java project [Central Library](https://github.com/ZCW-Summer25/CentralLibrary.git).
-
-The Java group builds that project, Data, you get to wrangle the data in the datasets below into a form that you agree with Java on. They load it, we get cool software.
-
-## Learning Objectives
-
-- pipelines - for real
-- data formats (csv, json)
-- wrangling data into useful formats
-
-## Need to Know
-
-- pandas
-- python data structures
-
-### Content Datasets
-
-and this is NOT public: https://zcw-students-projects.s3.us-east-1.amazonaws.com/LMSDataForWeek3Project/LMS-DataStuff.zip
-
-It contains the collected data for this project.
-You need to get it from an instructor, we're not gonna store it in this github repo, it's too Big.
-
-## The Pipeline Exercises
-
-
-These are the conceptual sub-projects.
-They will be useful in understanding how and what you need to do to provide Java with the data y'all need to make the project complete.
-
-https://github.com/ZCW-Summer25/PipelineOne
-https://github.com/ZCW-Summer25/PipelineTwo
-https://github.com/ZCW-Summer25/PipelineThree
-https://github.com/ZCW-Summer25/PipelineFour

Untitled.ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "980e2938-bd3c-4095-b123-59fcf1c8a572",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: 'data/raw/keywords.csv'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mFileNotFoundError\u001b[39m                         Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 3\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m pandas \u001b[38;5;28;01mas\u001b[39;00m pd\n\u001b[32m      2\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m numpy \u001b[38;5;28;01mas\u001b[39;00m np\n\u001b[32m----> \u001b[39m\u001b[32m3\u001b[39m df = pd.read_csv(\u001b[33m'data/raw/keywords.csv'\u001b[39m)\n\u001b[32m      4\u001b[39m \u001b[38;5;66;03m#---SHAPE---\u001b[39;00m\n\u001b[32m      5\u001b[39m print(f'Rows: {df.shape[\u001b[32m0\u001b[39m]:,} Columns: {df.shape[\u001b[32m1\u001b[39m]}')\n\u001b[32m      6\u001b[39m print()\n",
+      "\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.6_2/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:873\u001b[39m, in \u001b[36mread_csv\u001b[39m\u001b[34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, skip_blank_lines, parse_dates, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[39m\n\u001b[32m    861\u001b[39m kwds_defaults = _refine_defaults_read(\n\u001b[32m    862\u001b[39m     dialect,\n\u001b[32m    863\u001b[39m     delimiter,\n\u001b[32m   (...)\u001b[39m\u001b[32m    869\u001b[39m     dtype_backend=dtype_backend,\n\u001b[32m    870\u001b[39m )\n\u001b[32m    871\u001b[39m kwds.update(kwds_defaults)\n\u001b[32m--> \u001b[39m\u001b[32m873\u001b[39m \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",
+      "\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.6_2/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:300\u001b[39m, in \u001b[36m_read\u001b[39m\u001b[34m(filepath_or_buffer, kwds)\u001b[39m\n\u001b[32m    297\u001b[39m _validate_names(kwds.get(\u001b[33m\"\u001b[39m\u001b[33mnames\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[32m    299\u001b[39m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m300\u001b[39m parser = \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    302\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[32m    303\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
+      "\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.6_2/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:1645\u001b[39m, in \u001b[36mTextFileReader.__init__\u001b[39m\u001b[34m(self, f, engine, **kwds)\u001b[39m\n\u001b[32m   1642\u001b[39m     \u001b[38;5;28mself\u001b[39m.options[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m] = kwds[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m]\n\u001b[32m   1644\u001b[39m \u001b[38;5;28mself\u001b[39m.handles: IOHandles | \u001b[38;5;28;01mNone\u001b[39;00m = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1645\u001b[39m \u001b[38;5;28mself\u001b[39m._engine = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[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[43m.\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
+      "\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.6_2/libexec/lib/python3.14/site-packages/pandas/io/parsers/readers.py:1904\u001b[39m, in \u001b[36mTextFileReader._make_engine\u001b[39m\u001b[34m(self, f, engine)\u001b[39m\n\u001b[32m   1902\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[32m   1903\u001b[39m         mode += \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m-> \u001b[39m\u001b[32m1904\u001b[39m \u001b[38;5;28mself\u001b[39m.handles = \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m   1905\u001b[39m \u001b[43m    \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1906\u001b[39m \u001b[43m    \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1907\u001b[39m \u001b[43m    \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1908\u001b[39m \u001b[43m    \u001b[49m\u001b[43mcompression\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mcompression\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1909\u001b[39m \u001b[43m    \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmemory_map\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1910\u001b[39m \u001b[43m    \u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m=\u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1911\u001b[39m \u001b[43m    \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding_errors\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstrict\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1912\u001b[39m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstorage_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1913\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   1914\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m.handles \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[32m   1915\u001b[39m f = \u001b[38;5;28mself\u001b[39m.handles.handle\n",
+      "\u001b[36mFile \u001b[39m\u001b[32m/opt/homebrew/Cellar/jupyterlab/4.5.6_2/libexec/lib/python3.14/site-packages/pandas/io/common.py:926\u001b[39m, in \u001b[36mget_handle\u001b[39m\u001b[34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[39m\n\u001b[32m    921\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[32m    922\u001b[39m     \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[32m    923\u001b[39m     \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[32m    924\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m ioargs.encoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs.mode:\n\u001b[32m    925\u001b[39m         \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m926\u001b[39m         handle = \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[32m    927\u001b[39m \u001b[43m            \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    928\u001b[39m \u001b[43m            \u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    929\u001b[39m \u001b[43m            \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    930\u001b[39m \u001b[43m            \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    931\u001b[39m \u001b[43m            \u001b[49m\u001b[43mnewline\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m    932\u001b[39m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    933\u001b[39m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m    934\u001b[39m         \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[32m    935\u001b[39m         handle = \u001b[38;5;28mopen\u001b[39m(handle, ioargs.mode)\n",
+      "\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: 'data/raw/keywords.csv'"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "df = pd.read_csv('data/raw/keywords.csv')\n",
+    "#---SHAPE---\n",
+    "print(f'Rows: {df.shape[0]:,} Columns: {df.shape[1]}')\n",
+    "print()\n",
+    "#---Column Names and Types---\n",
+    "print(df.dtypes)\n",
+    "print()\n",
+    "#---First 5 Rows (visual check)---\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "36eacfc6-1a42-44f4-8669-01fecc069fde",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "387da07a-6cd8-407e-a53e-ccfdadf070c5",
+   "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": "3.14.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}