DATA201_projects/python_project_2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a8d466b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "pd.set_option('display.max_columns', None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1feb2733",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_13417/2268714868.py:1: DtypeWarning: Columns (18,20) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  df = pd.read_csv('~/Downloads/NYPD_Complaint_Data_Historic.csv')\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv('~/Downloads/NYPD_Complaint_Data_Historic.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5b1cdbba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['CMPLNT_NUM', 'CMPLNT_FR_DT', 'CMPLNT_FR_TM', 'CMPLNT_TO_DT',\n",
       "       'CMPLNT_TO_TM', 'ADDR_PCT_CD', 'RPT_DT', 'KY_CD', 'OFNS_DESC', 'PD_CD',\n",
       "       'PD_DESC', 'CRM_ATPT_CPTD_CD', 'LAW_CAT_CD', 'BORO_NM',\n",
       "       'LOC_OF_OCCUR_DESC', 'PREM_TYP_DESC', 'JURIS_DESC', 'JURISDICTION_CODE',\n",
       "       'PARKS_NM', 'HADEVELOPT', 'HOUSING_PSA', 'X_COORD_CD', 'Y_COORD_CD',\n",
       "       'SUSP_AGE_GROUP', 'SUSP_RACE', 'SUSP_SEX', 'TRANSIT_DISTRICT',\n",
       "       'Latitude', 'Longitude', 'Lat_Lon', 'PATROL_BORO', 'STATION_NAME',\n",
       "       'VIC_AGE_GROUP', 'VIC_RACE', 'VIC_SEX'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns\n",
    "# df.dtypes\n",
    "# df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1ac30b35",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# According to the data dictionary, CMPLNT_NUM (Complaint Number) is randomly generated and persistent.\n",
    "# Is it unique?\n",
    "\n",
    "df['CMPLNT_NUM'].is_unique"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "f0c76e18",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False    7821537\n",
       "True        3962\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# It's not unique. That's unexpected.\n",
    "\n",
    "df.duplicated(subset = 'CMPLNT_NUM').value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "253ab2f0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Since CMPLNT_NUM is not unique, we can't use it as an index.\n",
    "# Let's drop it.\n",
    "\n",
    "df.drop('CMPLNT_NUM', axis = 1, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7859f04c",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>CMPLNT_FR_DT</th>\n",
       "      <th>CMPLNT_FR_TM</th>\n",
       "      <th>CMPLNT_TO_DT</th>\n",
       "      <th>CMPLNT_TO_TM</th>\n",
       "      <th>ADDR_PCT_CD</th>\n",
       "      <th>RPT_DT</th>\n",
       "      <th>KY_CD</th>\n",
       "      <th>OFNS_DESC</th>\n",
       "      <th>PD_CD</th>\n",
       "      <th>PD_DESC</th>\n",
       "      <th>CRM_ATPT_CPTD_CD</th>\n",
       "      <th>LAW_CAT_CD</th>\n",
       "      <th>BORO_NM</th>\n",
       "      <th>LOC_OF_OCCUR_DESC</th>\n",
       "      <th>PREM_TYP_DESC</th>\n",
       "      <th>JURIS_DESC</th>\n",
       "      <th>JURISDICTION_CODE</th>\n",
       "      <th>PARKS_NM</th>\n",
       "      <th>HADEVELOPT</th>\n",
       "      <th>HOUSING_PSA</th>\n",
       "      <th>X_COORD_CD</th>\n",
       "      <th>Y_COORD_CD</th>\n",
       "      <th>SUSP_AGE_GROUP</th>\n",
       "      <th>SUSP_RACE</th>\n",
       "      <th>SUSP_SEX</th>\n",
       "      <th>TRANSIT_DISTRICT</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "      <th>Lat_Lon</th>\n",
       "      <th>PATROL_BORO</th>\n",
       "      <th>STATION_NAME</th>\n",
       "      <th>VIC_AGE_GROUP</th>\n",
       "      <th>VIC_RACE</th>\n",
       "      <th>VIC_SEX</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>12/31/2019</td>\n",
       "      <td>17:30:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>32.0</td>\n",
       "      <td>12/31/2019</td>\n",
       "      <td>118</td>\n",
       "      <td>DANGEROUS WEAPONS</td>\n",
       "      <td>793.0</td>\n",
       "      <td>WEAPONS POSSESSION 3</td>\n",
       "      <td>COMPLETED</td>\n",
       "      <td>FELONY</td>\n",
       "      <td>MANHATTAN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>STREET</td>\n",
       "      <td>N.Y. POLICE DEPT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>999937.0</td>\n",
       "      <td>238365.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40.820927</td>\n",
       "      <td>-73.943324</td>\n",
       "      <td>(40.82092679700002, -73.94332421899996)</td>\n",
       "      <td>PATROL BORO MAN NORTH</td>\n",
       "      <td>NaN</td>\n",
       "      <td>UNKNOWN</td>\n",
       "      <td>UNKNOWN</td>\n",
       "      <td>E</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12/29/2019</td>\n",
       "      <td>16:31:00</td>\n",
       "      <td>12/29/2019</td>\n",
       "      <td>16:54:00</td>\n",
       "      <td>47.0</td>\n",
       "      <td>12/29/2019</td>\n",
       "      <td>113</td>\n",
       "      <td>FORGERY</td>\n",
       "      <td>729.0</td>\n",
       "      <td>FORGERY,ETC.,UNCLASSIFIED-FELO</td>\n",
       "      <td>COMPLETED</td>\n",
       "      <td>FELONY</td>\n",
       "      <td>BRONX</td>\n",
       "      <td>NaN</td>\n",
       "      <td>STREET</td>\n",
       "      <td>N.Y. POLICE DEPT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1022508.0</td>\n",
       "      <td>261990.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40.885701</td>\n",
       "      <td>-73.861640</td>\n",
       "      <td>(40.885701406000074, -73.86164032499995)</td>\n",
       "      <td>PATROL BORO BRONX</td>\n",
       "      <td>NaN</td>\n",
       "      <td>UNKNOWN</td>\n",
       "      <td>UNKNOWN</td>\n",
       "      <td>E</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12/15/2019</td>\n",
       "      <td>18:45:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>109.0</td>\n",
       "      <td>12/29/2019</td>\n",
       "      <td>578</td>\n",
       "      <td>HARRASSMENT 2</td>\n",
       "      <td>638.0</td>\n",
       "      <td>HARASSMENT,SUBD 3,4,5</td>\n",
       "      <td>COMPLETED</td>\n",
       "      <td>VIOLATION</td>\n",
       "      <td>QUEENS</td>\n",
       "      <td>FRONT OF</td>\n",
       "      <td>STREET</td>\n",
       "      <td>N.Y. POLICE DEPT</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1034178.0</td>\n",
       "      <td>209758.0</td>\n",
       "      <td>25-44</td>\n",
       "      <td>UNKNOWN</td>\n",
       "      <td>M</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40.742281</td>\n",
       "      <td>-73.819824</td>\n",
       "      <td>(40.74228115600005, -73.81982408)</td>\n",
       "      <td>PATROL BORO QUEENS NORTH</td>\n",
       "      <td>NaN</td>\n",
       "      <td>25-44</td>\n",
       "      <td>WHITE HISPANIC</td>\n",
       "      <td>F</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  CMPLNT_FR_DT CMPLNT_FR_TM CMPLNT_TO_DT CMPLNT_TO_TM  ADDR_PCT_CD  \\\n",
       "0   12/31/2019     17:30:00          NaN          NaN         32.0   \n",
       "1   12/29/2019     16:31:00   12/29/2019     16:54:00         47.0   \n",
       "2   12/15/2019     18:45:00          NaN          NaN        109.0   \n",
       "\n",
       "       RPT_DT  KY_CD          OFNS_DESC  PD_CD  \\\n",
       "0  12/31/2019    118  DANGEROUS WEAPONS  793.0   \n",
       "1  12/29/2019    113            FORGERY  729.0   \n",
       "2  12/29/2019    578      HARRASSMENT 2  638.0   \n",
       "\n",
       "                          PD_DESC CRM_ATPT_CPTD_CD LAW_CAT_CD    BORO_NM  \\\n",
       "0            WEAPONS POSSESSION 3        COMPLETED     FELONY  MANHATTAN   \n",
       "1  FORGERY,ETC.,UNCLASSIFIED-FELO        COMPLETED     FELONY      BRONX   \n",
       "2           HARASSMENT,SUBD 3,4,5        COMPLETED  VIOLATION     QUEENS   \n",
       "\n",
       "  LOC_OF_OCCUR_DESC PREM_TYP_DESC        JURIS_DESC  JURISDICTION_CODE  \\\n",
       "0               NaN        STREET  N.Y. POLICE DEPT                0.0   \n",
       "1               NaN        STREET  N.Y. POLICE DEPT                0.0   \n",
       "2          FRONT OF        STREET  N.Y. POLICE DEPT                0.0   \n",
       "\n",
       "  PARKS_NM HADEVELOPT HOUSING_PSA  X_COORD_CD  Y_COORD_CD SUSP_AGE_GROUP  \\\n",
       "0      NaN        NaN         NaN    999937.0    238365.0            NaN   \n",
       "1      NaN        NaN         NaN   1022508.0    261990.0            NaN   \n",
       "2      NaN        NaN         NaN   1034178.0    209758.0          25-44   \n",
       "\n",
       "  SUSP_RACE SUSP_SEX  TRANSIT_DISTRICT   Latitude  Longitude  \\\n",
       "0       NaN      NaN               NaN  40.820927 -73.943324   \n",
       "1       NaN      NaN               NaN  40.885701 -73.861640   \n",
       "2   UNKNOWN        M               NaN  40.742281 -73.819824   \n",
       "\n",
       "                                    Lat_Lon               PATROL_BORO  \\\n",
       "0   (40.82092679700002, -73.94332421899996)     PATROL BORO MAN NORTH   \n",
       "1  (40.885701406000074, -73.86164032499995)         PATROL BORO BRONX   \n",
       "2         (40.74228115600005, -73.81982408)  PATROL BORO QUEENS NORTH   \n",
       "\n",
       "  STATION_NAME VIC_AGE_GROUP        VIC_RACE VIC_SEX  \n",
       "0          NaN       UNKNOWN         UNKNOWN       E  \n",
       "1          NaN       UNKNOWN         UNKNOWN       E  \n",
       "2          NaN         25-44  WHITE HISPANIC       F  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(3)\n",
    "# df.columns\n",
    "# df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "5fd666ad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "BORO           CRIME_CLASS\n",
       "BRONX          MISDEMEANOR    1000078\n",
       "               FELONY          466248\n",
       "               VIOLATION       227655\n",
       "BROOKLYN       MISDEMEANOR    1249836\n",
       "               FELONY          754414\n",
       "               VIOLATION       308893\n",
       "MANHATTAN      MISDEMEANOR    1075687\n",
       "               FELONY          597184\n",
       "               VIOLATION       209421\n",
       "QUEENS         MISDEMEANOR     826883\n",
       "               FELONY          516528\n",
       "               VIOLATION       218301\n",
       "STATEN ISLAND  MISDEMEANOR     210270\n",
       "               FELONY           81032\n",
       "               VIOLATION        70589\n",
       "Name: CRIME_CLASS, dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Question 1\n",
    "\n",
    "# How does each borough compare according to the class of crime committed?\n",
    "# But first, rename some columns to make the table more readable.\n",
    "\n",
    "df.rename(columns = {'LAW_CAT_CD': 'CRIME_CLASS', 'BORO_NM': 'BORO'}, inplace = True)\n",
    "df.groupby(['BORO'])['CRIME_CLASS'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3cbcbd7c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='BORO,CRIME_CLASS'>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# A quick visualization of the above\n",
    "\n",
    "df.groupby(['BORO'])['CRIME_CLASS'].value_counts().plot(kind = 'bar', figsize = (10, 5))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "b07d2228",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6761"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# df.head(25)\n",
    "# df['OFNS_DESC'].isna().sum()\n",
    "df['PD_DESC'].isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "1ef4d375",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Question 2\n",
    "\n",
    "# Some incidents occurred in NYC parks, playgrounds or greenspaces.\n",
    "# What crimes were reported most often and where?\n",
    "\n",
    "# Again, let's begin by renaming columns.\n",
    "\n",
    "df.rename(columns = {'PARKS_NM': 'PUBLIC_SPACE',\n",
    "                     'PD_DESC': 'DESCRIPTION',\n",
    "                     'ADDR_PCT_CD': 'PRECINCT',\n",
    "                     'Lat_Lon': 'LOCATION',\n",
    "                     'CMPLNT_FR_DT': 'DATE',\n",
    "                     'CMPLNT_FR_TM': 'TIME'\n",
    "                    }, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "b838819a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# PD_DESC and OFNS_DESC are both descriptions of the incident.\n",
    "# The former is more granular, according to the data dictionary.\n",
    "# Also, it has fewer NaNs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "e9c16848",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CENTRAL PARK                      1856\n",
       "FLUSHING MEADOWS CORONA PARK      1532\n",
       "CONEY ISLAND BEACH & BOARDWALK    1161\n",
       "WASHINGTON SQUARE PARK            1063\n",
       "RIVERSIDE PARK                     680\n",
       "PROSPECT PARK                      616\n",
       "UNION SQUARE PARK                  599\n",
       "MARCUS GARVEY PARK                 469\n",
       "RANDALL'S ISLAND PARK              454\n",
       "SARA D. ROOSEVELT PARK             395\n",
       "BRYANT PARK                        354\n",
       "ST. MARY'S PARK BRONX              354\n",
       "CLAREMONT PARK                     348\n",
       "MACOMBS DAM PARK                   341\n",
       "CROTONA PARK                       319\n",
       "Name: PUBLIC_SPACE, dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's choose public spaces to compare.\n",
    "\n",
    "# df.head()\n",
    "df['PUBLIC_SPACE'].sort_values(ascending = False).value_counts().head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "91ae572a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LARCENY,PETIT FROM OPEN AREAS,                                  563\n",
       "LARCENY,GRAND FROM OPEN AREAS, UNATTENDED                       501\n",
       "ASSAULT 3                                                       473\n",
       "CONTROLLED SUBSTANCE, POSSESSI                                  272\n",
       "HARASSMENT,SUBD 3,4,5                                           252\n",
       "CRIMINAL MISCHIEF 4TH, GRAFFIT                                  209\n",
       "ASSAULT 2,1,UNCLASSIFIED                                        187\n",
       "HARASSMENT,SUBD 1,CIVILIAN                                      187\n",
       "MARIJUANA, POSSESSION 4 & 5                                     174\n",
       "ROBBERY,OPEN AREA UNCLASSIFIED                                  143\n",
       "LARCENY,PETIT OF VEHICLE ACCES                                  141\n",
       "LARCENY,PETIT FROM BUILDING,UN                                  133\n",
       "LARCENY,PETIT OF BICYCLE                                        131\n",
       "ROBBERY,PERSONAL ELECTRONIC DEVICE                              115\n",
       "LEWDNESS,PUBLIC                                                  91\n",
       "SEXUAL ABUSE 3,2                                                 77\n",
       "LARCENY,GRAND FROM BUILDING (NON-RESIDENCE) UNATTENDED           71\n",
       "CRIMINAL MISCHIEF,UNCLASSIFIED 4                                 66\n",
       "MENACING,UNCLASSIFIED                                            66\n",
       "MARIJUANA, SALE 4 & 5                                            65\n",
       "LARCENY,GRAND FROM PERSON,PICK                                   64\n",
       "RESISTING ARREST                                                 63\n",
       "LARCENY,GRAND FROM VEHICLE/MOTORCYCLE                            59\n",
       "LARCENY,PETIT BY DISHONEST EMP                                   54\n",
       "WEAPONS, POSSESSION, ETC                                         53\n",
       "MISCHIEF, CRIMINAL 4, OF MOTOR                                   53\n",
       "PUBLIC ADMINISTATION,UNCLASS M                                   52\n",
       "ASSAULT POLICE/PEACE OFFICER                                     47\n",
       "FORGERY,ETC.-MISD.                                               46\n",
       "AGGRAVATED HARASSMENT 2                                          45\n",
       "LARCENY,GRAND FROM PERSON,PERSONAL ELECTRONIC DEVICE(SNATCH)     45\n",
       "LARCENY,PETIT FROM AUTO                                          44\n",
       "BURGLARY,COMMERCIAL,NIGHT                                        36\n",
       "LEAVING SCENE-ACCIDENT-PERSONA                                   33\n",
       "LARCENY,GRAND FROM PERSON, BAG OPEN/DIP                          33\n",
       "RECKLESS ENDANGERMENT 2                                          31\n",
       "CONTROLLED SUBSTANCE,INTENT TO                                   31\n",
       "BRIBERY,PUBLIC ADMINISTRATION                                    30\n",
       "LARCENY,GRAND BY THEFT OF CREDIT CARD                            27\n",
       "RAPE 1                                                           26\n",
       "MISCHIEF, CRIMINAL 3 & 2, OF M                                   26\n",
       "WEAPONS POSSESSION 3                                             26\n",
       "LARCENY,GRAND OF BICYCLE                                         25\n",
       "LARCENY,PETIT FROM STORE-SHOPL                                   24\n",
       "LARCENY,GRAND BY ACQUIRING LOST CREDIT CARD                      23\n",
       "LARCENY,GRAND FROM PERSON,UNCL                                   22\n",
       "LARCENY,PETIT BY ACQUIRING LOS                                   21\n",
       "ROBBERY,BICYCLE                                                  21\n",
       "LARCENY,GRAND OF AUTO                                            20\n",
       "RECKLESS ENDANGERMENT 1                                          19\n",
       "Name: DESCRIPTION, dtype: int64"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Each of the top four have more than 1000 incidents.\n",
    "# What kind of incidents occurred there?\n",
    "\n",
    "subset = df[(df['PUBLIC_SPACE'] == 'CENTRAL PARK')\n",
    "            | (df['PUBLIC_SPACE'] == 'FLUSHING MEADOWS CORONA PARK')\n",
    "            | (df['PUBLIC_SPACE'] == 'CONEY ISLAND BEACH & BOARDWALK')\n",
    "            | (df['PUBLIC_SPACE'] == 'WASHINGTON SQUARE PARK')\n",
    "           ]\n",
    "subset['DESCRIPTION'].value_counts().head(50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "30c5dab8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Many incidents. This is grim.\n",
    "# Choose just a few (to avoid psychological fatigue).\n",
    "\n",
    "bikes = subset[subset['DESCRIPTION'].str.contains('BICYCLE')]\n",
    "cars = subset[subset['DESCRIPTION'].str.contains('VEHICLE')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "be093f45",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='PUBLIC_SPACE'>"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualizations comparing these two incidents in each location\n",
    "# I wonder if there's a way to combine them into one plot using different colors.\n",
    "\n",
    "bikes.groupby(['PUBLIC_SPACE'])['DESCRIPTION'].count().plot(kind = 'bar')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "c52dda8e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='PUBLIC_SPACE'>"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cars.groupby(['PUBLIC_SPACE'])['DESCRIPTION'].count().plot(kind = 'bar')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "483a4ff9",
   "metadata": {},
   "source": [
    "## Conclusions\n",
    "\n",
    "### The dataset comprises NYPD criminal complaints from 2006 to 2019. The downloaded csv file contains more than 7 million rows and 35 columns. The complaint number for each row was found to be non-unique. Exploratory analysis shows the dataset to be well formatted, with mostly string type data providing time, date, location and descriptions of each incident. No columns seemed to contain numerical data that would merit any summary statistics.\n",
    "\n",
    "### The first research question looks at the category of each incident and where those incidents occurred. I made a visualization to show the number of felony, misdemeanor and violations for each borough.\n",
    "\n",
    "### The second research quesion intended to show the top criminal complaints that occurred in NYC parks, playgrounds and greenspaces. But the task was found to be a nauseating experience, so I abandoned it. Instead, I compared the number of bike and car incidents for each of these public spaces. All incidents involving bikes or cars were considered: e.g. theft of, assault with, damage to, etc. Plotting showed Central Park to be where the greatest number of bike incidents occurred, but very few car incidents. Surprisingly, Flushing Meadows Park was very high for cars, whereas Washington Square Park had no car incidents at all."
   ]
  }
 ],
 "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": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}