updated naming of notebooks

src/dea_0_python.ipynb → src/0_introduction.ipynb

@@ -10,11 +10,22 @@
     "\n",
     "Eva Zangerle\n",
     "\n",
+    "## Overview of Notebooks\n",
+    "* Datasets: [3_datasets.ipynb](3_datasets.ipynb)\n",
+    "* Data Preparation and Quality: [4_data_preparation_quality.ipynb](4_data_preparation_quality.ipynb)\n",
+    "* Feature Engineering: [5_feature_engineering.ipynb](5_feature_engineering.ipynb)\n",
+    "* Dataset Analyses: [6_dataset_analyses.ipynb](6_dataset_analyses.ipynb)\n",
+    "* Hypotheses and Evaluation: [7_hypotheses_evaluation.ipynb](7_hypotheses_evaluation.ipynb)\n",
+    "* Modeling and Prediction: [8_modeling_prediction.ipynb](8_modeling_prediction.ipynb)\n",
+    "* Reproducible Research: [9_reproducible_research.ipynb](9_reproducible_research.ipynb)\n",
+    "\n",
+    "\n",
     "## General Notes\n",
     "* Code is partly taken from further sources, such as books.\n",
     "* Sources are annotated (and acknowledged!) as follows:\n",
     "    * (CleaningData): Cleaning Data for Effective Data Science: Doing the other 80% of the work with Python, R, and command-line tools; David Mertz; Packt Publishing, 2021; [Github repo](https://github.com/PacktPublishing/Cleaning-Data-for-Effective-Data-Science/)\n",
     "* Unless marked otherwise, code was written by Eva Zangerle.\n",
+    "* I deliberately mix different Python packages (e.g., for visualization matplotlib, pandas and seaborn) to showcase their use.\n",
     "\n",
     "\n",
     "\n",
@@ -36,6 +47,16 @@
     "## Further tools\n",
     "* jq command linen json processor: https://stedolan.github.io/jq/\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f6860d72-11e4-4574-b20b-7884a6653abc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    " "
+   ]
   }
  ],
  "metadata": {

src/6_dataset_analyses.ipynb

+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/dea_5_visualization.ipynb

-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "b5576d1e-7912-4308-ae7d-d6b0571ade38",
-   "metadata": {},
-   "source": [
-    "# Visualization"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "072aa23b-1c58-4b80-a8d4-28db8e1d60fc",
-   "metadata": {},
-   "source": [
-    "todo:\n",
-    "* plotly and handcuffs (also add to start.py) as follows:\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "557c1313-8fb5-4222-9064-961d8f51f744",
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'plotly'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-1-3bacd8ca2d3f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# Visualization\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mplotly\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplotly\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpy\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mplotly\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgraph_objs\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mgo\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mplotly\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moffline\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0miplot\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minit_notebook_mode\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0minit_notebook_mode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconnected\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'plotly'"
-     ]
-    }
-   ],
-   "source": [
-    "\n",
-    "# Visualization\n",
-    "import plotly.plotly as py\n",
-    "import plotly.graph_objs as go\n",
-    "from plotly.offline import iplot, init_notebook_mode\n",
-    "init_notebook_mode(connected=True)\n",
-    "import cufflinks as cf\n",
-    "cf.go_offline(connected=True)\n",
-    "cf.set_config_file(theme='pearl')\n",
-    "\n",
-    "print('Your favorite libraries have been loaded.')\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "68da3423-ec0c-4f31-866f-01288666cbe6",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "42cf0d5f-6c8d-4fbd-9f08-37dc11f27fc9",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "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": "3.9.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

src/dea_6_data_dimensions.ipynb

-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "be4ee762-b4c6-421b-beec-ec63bd8c13a5",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "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": "3.9.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}