anal 2 coords

coordinates added to analysis 2

analysis/analysis2.ipynb

@@ -410,7 +410,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 91,
+   "execution_count": 93,
    "metadata": {},
    "outputs": [
     {
@@ -460,7 +460,99 @@
     "\n",
     "print(df2.describe())\n",
     "print(\"------------------------------------------------------------------------\")\n",
-    "print(df2)"
+    "print(df2)\n",
+    "\n",
+    "df2.to_csv(\"../data/processed/tax_and_gay.csv\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                zip     population  gay tax rate  overall tax paid  income  \\\n",
+      "count   2184.000000    2184.000000   2184.000000       2184.000000  2184.0   \n",
+      "mean   48935.203297   26691.730769   4373.997253        596.719322     1.0   \n",
+      "std    35451.335807   17960.713867   3054.620840        615.174358     0.0   \n",
+      "min     1730.000000     160.000000      0.000000          0.000000     1.0   \n",
+      "25%    11360.750000   13337.500000   2110.000000        217.000000     1.0   \n",
+      "50%    60023.500000   24070.000000   3900.000000        434.000000     1.0   \n",
+      "75%    80227.250000   35640.000000   5902.500000        777.250000     1.0   \n",
+      "max    98686.000000  114420.000000  24560.000000       9166.000000     1.0   \n",
+      "\n",
+      "               lat         long  \n",
+      "count  2184.000000  2184.000000  \n",
+      "mean     38.016518   -91.296804  \n",
+      "std       5.210272    18.476699  \n",
+      "min      25.572213  -123.118977  \n",
+      "25%      33.997027  -105.037767  \n",
+      "50%      39.930150   -87.603617  \n",
+      "75%      40.960828   -74.310179  \n",
+      "max      47.916786   -70.758184  \n",
+      "------------------------------------------------------------------------\n",
+      "        zip  population  gay tax rate  overall tax paid  income        lat  \\\n",
+      "0      1730     13570.0          3260             150.0       1  42.499295   \n",
+      "1      1731      2450.0           550               0.0       1  42.456748   \n",
+      "2      1742     17170.0          4220             297.0       1  42.462911   \n",
+      "3      1760     34350.0          7880             468.0       1  42.284822   \n",
+      "4      1770      4310.0          1060              46.0       1  42.231947   \n",
+      "...     ...         ...           ...               ...     ...        ...   \n",
+      "2179  98682     57010.0         11080             703.0       1  45.673209   \n",
+      "2180  98683     30700.0          6470             358.0       1  45.603287   \n",
+      "2181  98684     27630.0          5390             371.0       1  45.630556   \n",
+      "2182  98685     27540.0          6490             298.0       1  45.715211   \n",
+      "2183  98686     17800.0          4120             215.0       1  45.723392   \n",
+      "\n",
+      "            long  \n",
+      "0     -71.281889  \n",
+      "1     -71.279484  \n",
+      "2     -71.364496  \n",
+      "3     -71.348811  \n",
+      "4     -71.372963  \n",
+      "...          ...  \n",
+      "2179 -122.481745  \n",
+      "2180 -122.510170  \n",
+      "2181 -122.514839  \n",
+      "2182 -122.693165  \n",
+      "2183 -122.624397  \n",
+      "\n",
+      "[2184 rows x 7 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "## take the dataset & add long/lat\n",
+    "## props to Nat for creating the backbone I used to zipcode -> long/lat\n",
+    "\n",
+    "cords = pd.read_csv(\"../data/raw/zip_lat_long.csv\")\n",
+    "gaydf = pd.read_csv(\"../data/processed/tax_and_gay.csv\")\n",
+    "\n",
+    "# Let's add long/lat columns to gb\n",
+    "gaydf = gaydf.merge(cords, left_on=\"zip\", right_on=\"ZIP\")\n",
+    "\n",
+    "# // unneded was already filtered out\n",
+    "\n",
+    "# There's a lot of info baked into some of these columns. Especially the composite indexes.\n",
+    "# We'll leave their names as is for easy reference even if they're a little ugly.\n",
+    "gaydf = gaydf.rename({\n",
+    "    \"LAT\": \"lat\",\n",
+    "    \"LNG\": \"long\",\n",
+    "}, axis=\"columns\")\n",
+    "\n",
+    "# gb.to_csv(\"../data/processed/gaybourhoods-nat.csv\")\n",
+    "# gb.head()\n",
+    "\n",
+    "# unperson unneccesary zip codes\n",
+    "del gaydf['zip.1']\n",
+    "del gaydf['ZIP']\n",
+    "\n",
+    "print(gaydf.describe())\n",
+    "print(\"------------------------------------------------------------------------\")\n",
+    "print(gaydf)"
    ]
   },
   {
@@ -469,8 +561,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "\n",
     "#compare taxes paid by queers to taxes paid by general"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {