notebook edits

jacksmion · Jun 29, 2021 · 6332008 · 6332008
1 parent b57fdec
commit 6332008
Show file tree

Hide file tree

Showing 3 changed files with 180 additions and 45 deletions.
diff --git a/...views-2/solution/notebook-filtering.ipynb → ...Hotel-Reviews-2/solution/1-notebook.ipynb b/...views-2/solution/notebook-filtering.ipynb → ...Hotel-Reviews-2/solution/1-notebook.ipynb
@@ -10,16 +10,23 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": 3
+   "version": "3.7.0"
   },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3.7.0 64-bit ('3.7')"
+  },
+  "interpreter": {
+   "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2,
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -30,7 +37,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -54,7 +61,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -65,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -75,7 +82,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -85,7 +92,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -98,7 +105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -118,23 +125,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
     "# No longer need any of these columns\n",
-    "df.drop([\"Tags\", \"Review_Date\", \"Review_Total_Negative_Word_Counts\", \"Review_Total_Positive_Word_Counts\", \"days_since_review\", \"Total_Number_of_Reviews_Reviewer_Has_Given\"], axis = 1, inplace=True)\n"
+    "df.drop([\"Review_Date\", \"Review_Total_Negative_Word_Counts\", \"Review_Total_Positive_Word_Counts\", \"days_since_review\", \"Total_Number_of_Reviews_Reviewer_Has_Given\"], axis = 1, inplace=True)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Saving results to Hotel_Reviews_Filtered.csv\n",
+      "Filtering took 23.74 seconds\n"
+     ]
+    }
+   ],
    "source": [
     "# Saving new data file with calculated columns\n",
     "print(\"Saving results to Hotel_Reviews_Filtered.csv\")\n",
-    "df.to_csv(r'Hotel_Reviews_Filtered.csv', index = False)\n",
+    "df.to_csv(r'../../data/Hotel_Reviews_Filtered.csv', index = False)\n",
     "end = time.time()\n",
     "print(\"Filtering took \" + str(round(end - start, 2)) + \" seconds\")\n"
    ]

diff --git a/...el-Reviews-2/solution/notebook-tags.ipynb → ...Hotel-Reviews-2/solution/2-notebook.ipynb b/...el-Reviews-2/solution/notebook-tags.ipynb → ...Hotel-Reviews-2/solution/2-notebook.ipynb
@@ -10,26 +10,35 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": 3
+   "version": "3.7.0"
   },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3.7.0 64-bit ('3.7')"
+  },
+  "interpreter": {
+   "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2,
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Load the hotel reviews from CSV (you can )\n",
+    "import pandas as pd \n",
+    "\n",
     "df = pd.read_csv('../../data/Hotel_Reviews_Filtered.csv')\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +62,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -68,7 +77,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -78,9 +87,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "The shape of the tags with no filtering: (2514684, 2)\n",
+      "                        index   count\n",
+      "0                Leisure trip  338423\n",
+      "1                      Couple  205305\n",
+      "2               Solo traveler   89779\n",
+      "3               Business trip   68176\n",
+      "4                       Group   51593\n",
+      "5  Family with young children   49318\n",
+      "6  Family with older children   21509\n",
+      "7      Travelers with friends    1610\n",
+      "8                  With a pet    1078\n"
+     ]
+    }
+   ],
    "source": [
     "# Get the value counts\n",
     "tag_vc = df_tags.value.value_counts()\n",