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_6745/2268714868.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": 12,
   "id": "3cbcbd7c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='BORO,CRIME_CLASS'>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "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": 15,
   "id": "b07d2228",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6761"
      ]
     },
     "execution_count": 15,
     "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": 18,
   "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": 19,
   "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": 35,
   "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": 35,
     "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": null,
   "id": "91ae572a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Each of the top four have more than 1000 incidents.\n",
    "# We'll pick Central Park and Coney Island."
   ]
  }
 ],
 "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
}