· Project Description/Outline: Our goal is to analyze Traffic violations data for the major US cities. With our analysis, we want to understand what are the primary reasons for violations, demography,...

{
"cells": [
{
"cell_type": "code",
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": [
"#imports\n",
"import re\n",
"import warnings\n",
"import numpy as np\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"\n",
"#Setting environment variables\n",
"pd.options.display.max_columns = 50\n",
"warnings.filterwarnings(\"ignore\")\n",
"sns.set_style(\"darkgrid\")\n",
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Data Ingestion\n",
"1. Reading data using Pandas. Pandas is very powerful and popular li
ary to deal with CSV data in a DataFrame format.\n",
"2. Loading 10,000 rows only to avoid memory issues. Pandas provides generator functions also to account for data which are memory bound."
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [],
"source": [
"#############################\n",
"# READING DATA \n",
"# 1. IMPORTING DATA INTO PANDAS DATAFRAME\n",
"# 2. LOADING 10K ROWS DUE TO OUT OF MEMORY ERROR\n",
"#############################\n",
"\n",
"df = pd.read_csv(\"Traffic_Violations.csv\", nrows=10000)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Data Overview\n",
"1. Dataframe properties depicting data type identified in each data field/column\n",
"2. Cleaning data of values which are NaNs.\n",
"3. Replacing NaNs with 0s to avoid data information loss"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Data Dimensions\n",
"Rows 10000, Columns 35\n",
"Date Of Stop object\n",
"Time Of Stop object\n",
"Agency object\n",
"SubAgency object\n",
"Description object\n",
"Location object\n",
"Latitude float64\n",
"Longitude float64\n",
"Accident object\n",
"Belts object\n",
"Personal Injury object\n",
"Property Damage object\n",
"Fatal object\n",
"Commercial License object\n",
"HAZMAT object\n",
"Commercial Vehicle object\n",
"Alcohol object\n",
"Work Zone object\n",
"State object\n",
"VehicleType object\n",
"Year float64\n",
"Make object\n",
"Model object\n",
"Color object\n",
"Violation Type object\n",
"Charge object\n",
"Article object\n",
"Contributed To Accident object\n",
"Race object\n",
"Gender object\n",
"Driver City object\n",
"Driver State object\n",
"DL State object\n",
"A
est Type object\n",
"Geolocation object\n",
"dtype: object\n",
"NULL values for each column\n",
" Column name\n",
"Date Of Stop 0\n",
"Time Of Stop 0\n",
"Agency 0\n",
"SubAgency 0\n",
"Description 0\n",
"Location 0\n",
"Latitude 770\n",
"Longitude 770\n",
"Accident 0\n",
"Belts 0\n",
"Personal Injury 0\n",
"Property Damage 0\n",
"Fatal 0\n",
"Commercial License 0\n",
"HAZMAT 0\n",
"Commercial Vehicle 0\n",
"Alcohol 0\n",
"Work Zone 0\n",
"State 0\n",
"VehicleType 0\n",
"Year 74\n",
"Make 0\n",
"Model 0\n",
"Color 133\n",
"Violation Type 0\n",
"Charge 0\n",
"Article 323\n",
"Contributed To Accident 0\n",
"Race 0\n",
"Gender 0\n",
"Driver City 11\n",
"Driver State 0\n",
"DL State 8\n",
"A
est Type 0\n",
"Geolocation 770\n",
"NULL values % for each column\n",
" Column name\n",
"Date Of Stop 0.00\n",
"Time Of Stop 0.00\n",
"Agency 0.00\n",
"SubAgency 0.00\n",
"Description 0.00\n",
"Location 0.00\n",
"Latitude 7.70\n",
"Longitude 7.70\n",
"Accident 0.00\n",
"Belts 0.00\n",
"Personal Injury 0.00\n",
"Property Damage 0.00\n",
"Fatal 0.00\n",
"Commercial License 0.00\n",
"HAZMAT 0.00\n",
"Commercial Vehicle 0.00\n",
"Alcohol 0.00\n",
"Work Zone 0.00\n",
"State 0.00\n",
"VehicleType 0.00\n",
"Year 0.74\n",
"Make 0.00\n",
"Model 0.00\n",
"Color 1.33\n",
"Violation Type 0.00\n",
"Charge 0.00\n",
"Article 3.23\n",
"Contributed To Accident 0.00\n",
"Race 0.00\n",
"Gender 0.00\n",
"Driver City 0.11\n",
"Driver State 0.00\n",
"DL State 0.08\n",
"A
est Type 0.00\n",
"Geolocation 7.70\n"
]
}
],
"source": [
"#############################\n",
"# 1. QUICK OVERVIEW OF DATA\n",
"# 2. DATAFRAME PROPERTIES\n",
"# 3. CLEAN DATA OF NAN/NULL VALUES\n",
"#############################\n",
"print (\"Data Dimensions\")\n",
"print (\"Rows %d, Columns %d\"%(df.shape))\n",
"print (df.dtypes)\n",
"\n",
"\n",
"print (\"NULL values for each column\")\n",
"column_nulls = pd.DataFrame(df.isnull().sum())\n",
"column_nulls.columns = ['Column name']\n",
"print (column_nulls)\n",
"\n",
"print (\"NULL values % for each column\")\n",
"column_nulls_percentage = pd.DataFrame((df.isnull().sum()/df.shape[0])*100)\n",
"column_nulls_percentage.columns = ['Column name']\n",
"print (column_nulls_percentage)\n",
"\n",
"#Filling NaNs with 0\n",
"df = df.fillna(0)"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [],
"source": [
"# 1. Gathering relevant data for Exploratory Data Analysis\n",
"# 2. Taking only columns which are specified in the assignment\n",
"\n",
"column_names = [\"Race\", \"Gender\", \"Driver City\", \"Driver State\", \\\n",
" \"Location\", \"Longitude\", \"Latitude\", \"Fatal\", \"Violation Type\"]\n",
"df = df[column_names]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Data Analysis\n",
"1. Some data analyis on understanding the **trend** of violations accross U.S\n",
"2. Plotting graphs to understand easily\n",
"3. An explanation to make understanding cleaner"
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Aggregated count of Violations by RACE\n",
" Race Count\n",
"0 BLACK 3428\n",
"1 WHITE 2960\n",
"2 HISPANIC 2550\n",
"3 ASIAN 540\n",
"4 OTHER 511\n",
"5 NATIVE AMERICAN 11\n"
]
},
{
"data": {
"image/png": "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
ZckKaU8O53Vya+XUg5MZ9Vz31LKDulE9H5JBpL8Y5J31lpXrz1ZKWX7JB9Psnc6AXxXkiOSzExnFbevlHJHkuuTvKzW+uellNndY
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
JF9P8vIkr0nyd904HWro/x9PTDJp8IZSynFJLk1yd5Irk3wmnVuiN2TiMM8PPu993YhNOrdAD3eunySZVErZa8hYHlFKuaaU8ugRxj70vJMH/X401x/OmkG/n5BOXCed+H99OreUL+gG7gZ1V7mPTzI9v1sNnp3k2nQ+1/yddFbB11rdHWe6+87s3obel+TTtdb9urG9fzq
ctG+XoAGGeiGADG1seSvDKdW2w/uoF9vpbkzaWUCaWU7dK5zf
Q/Z5fpL5tdZLk9Qkh6YTZEkn2NaL6F
XUkWpfNty+l+bvk1w5x3g7qr1h9I8qlSyiO759kuyXlJtq+1/qo79jeWUiaVUiZ2r7f2GrelE4gppcxJ8qhRXPZBr2WI13Tfpx3Tub157Srvv6azsn1yOp+jHs3ruy/JcUmOLaWsjdnbkpxZa/1aOqvGKaX0Jfm/SV5aSpnRPfy9SU5M8k9JXlFKWfva3pjO56UB6BGiGADGUK11YZKdk9xZa71uA7u9JcmuSa7
qpJzhqyz4fSibdr04mu/0jntt10H7+olHLBkGNemeS5pZTrknw/nduF52/k+N/XPe5r3Wv/KJ0V2hd3dzkzyS3prLD+NJ2gPaH73NuTnNA97ugkPxzFJf8ryZpSyvdLKcOtHt/RPc+/Jrmg+/6u9TdJfvUQ7/Nwr+876dxqfWE6Mb8kSS2l/GeS/5VOJO9Va72me/7vdt/P3dL5crKvpfMXB18vpfw4nZXql
xTgC9Y8LAgP/NBgB6WymlP52fN/y3Q79FGwAeipViAKCnlVJ+P50V3TuTXD3OwwGgx1gpBgAAoFlWigEAAGiWKAYAAKBZohgAAIBm9Y/3ABgbDzzwwMCaNdvO58X7+iZkWxoPo2fuepe5623mr3eZu95m/nqXuetdYzV3kyb13Z5k1kj7ieKHqTVrBrJ8+d3jPYx1Zs6cuk2Nh9Ezd73L3PU289e7zF1vM3+9y9z1
Gau1mzpv9yNPu5fRoAAIBmiWIAAACaJYoBAABols8UAwAAjGDNmtVZtuy2rF5933gP5WHn1lsnZGBg079oq79/cnbccVb6+jYtb0UxAADACJYtuy2PeMTUbL/9bpkwYcJ4D+dhpa9vYtaseWCTjh0YGMjKlXdm2bLbsssuj9qkc7h9GgAAYASrV9+X7befIYi3MRMmTMj228/YrBV8UQwAADAKgnjbtLnzIooBAAC2cccff0x++MMfrLft
6Q/nSl76Q88
cG655ZYNHvuylx2ae++9d4PPf/vb38rtt9+W3/zm9nzoQ2dv1jgfeOCBXH75p/KmNx2V448/JnPnHps
vj5Zp1zsGuv/Y/8/OfXb7HzJaIYAABgi1uw+Krsf/k+eeTHdsj+l++TBYuv2qzzHXroX+SrX/3Kusf3339/vvvdf8mf/dnzc8IJJ2W33X
5HNfffVnsnLlyuy88y45+eRTN2ucV1xxee64Y3kuvPDiXHjhxXnTm96SU089KatXr96s8671la98MbffftsWOddavmgLAABgC1qw+KqcuHBuVq1elSRZsuLmnLhwbpLksL0P36RzHnjgc/OJT3w099xzTx7xiEfkX/7l23na0w7IlClTcvzxx+Rtb3tndtpp55xxxruzcuXKrFmzJkcffVz+6I+euu4cN97481xwwXl54IEHsnz58px88qm566678vOfL86ZZ74n7373GTnzzNNy8cXz84MfLMrFF3882223XWbM2CHveMd7cv31NVdccXkmTerPr361NM997kE58sg3rDfOL37x87n00k9n4sTO+usTn7hPLrnksvT392fx4p/lvPM+mL6+vkyePDmnnPKuDAw8kPe+9535xCfmJ0mOOea1Of309+Waa76UX
6V1m2bFluvfXXmTv3xOyww8x873v/lsWLf5Y993zcZv1FwGBWigEAALagsxadvi6I11q1elXOWnT6Jp9zu+22y5/8yYH553/+VpLkmmu+mBe/+KXr7XPZZZfmKU85IB/96Cdzxhln5+yzz1jvRx3ddNONOf74t+b88z+eV77yyFxzzZfyjGc8K3vttXfe9a6/yqRJk5J0vtH5nHPel/e974O58MKLs99+++eyyy5Nktx6669z5pnn5BOfmJ8
7z8QeO89957MmPGjPW27bDDzCTJBz5wVk488ZRceOHFeclLXpYLLzz3IV/zpEmT8+EPfyQnnHBSPve5K/OEJzwxBxzw9Bx33Fu2WBAnohgAAGCLWrpiyUZtH61DD31JvvrVa3L
f+Tu+66K3vv/YT1nv/lL2/Kfvs9OUkya9aumTp1+yxb9tt1z++yy66ZP/+SnHnmaVm48BsbvKV5+fLlmTp1+8yatWuSZL/9npy
oxSfK4x+2V/v7+TJkyJdtt94gHHTt9+vSsXLlivW3f/va3snLlitx++235vd8rSZInPWn/deccbHDE7713Z99dd90t99234c9Eby5RDAAAsAXtPm32Rm0frcc/fq+sWrUyV1/92RxyyIse9PxjHvPY/OhH1yZJN5zvzIwZO6x7/vzzP5g3vOHYvOtdp+fxj99rXYBOnDgxDzzwu58TPHPmzNx998rcfvvtSTpf
XHHv8rSTLSFz2/4AV/nk996pPrzn3ddT/KhReel8mTt8suu8xa9yVZa885efLkLFu2LGvWrMldd92VX
6V+vONdy1JkyYkIGBTfuZxhviM8UAAABb0Lw5p633meIkmdI/JfPmnLbZ5z7kkBflox/9SBYs+PKDnnvNa16X97
7Jw4Tdy77335pRT5qW
3fJd9BBB+fd7357pk+fkVmzds0ddyxPkuy77x/mzDNPyymnzEvSCc9TTpmXefPelokTJ2T69Bl55zvfmxtvHPlbpI844tW55JKLcuyxr0t/f3/6+/tz9tnnZtKkSXn72+flvPPOycDAQPr6+nLqqe/Ozjvvkqc+9YAcffRr8uhHz87s2Xs85Pl
f3zUUXXZhHPWr37LnnYzfmrdugCYOXp3n4uP/+NQPLl9893sNYZ+bMqdmWxsPombveZe56m/nrXeaut5m/3jXWc3fLL
M
s9ZtT7L1h8Vc5adHqWrliS3afNzrw5p23yl2w93PX1TcyaNZu3+jvc/MyaNf2HSZ4y0rFWigEAALaww/Y+XAT3CJ8pBgAAoFmiGAAAgGaJYgAAgFHwfUzbps2dF1EMAAAwgv7+yVm58k5hvI0ZGBjIypV3pr9/8iafwxdtAQAAjGDHHWdl2bLbsmLF8vEeysNO52cP
pfNvT3T86OO87a9OM3+UgAAIBG9PX1Z5ddHjXew3hYGu8fheb2aQAAAJoligEAAGiWKAYAAKBZohgAAIBmiWIAAACaJYoBAABoligGAACgWaIYAACAZoliAAAAmiWKAQAAaJYoBgAAoFmiGAAAgGaJYgAAAJoligEAAGiWKAYAAKBZohgAAIBmiWIAAACaJYoBAABoligGAACgWaIYAACAZoliAAAAmiWKAQAAaJYoBgAAoFn9W/qEpZQDk/xDkn1
Td3t52d5Ge11vndx09L8p0kz6y1/qC77YokuyfZM8l9SX6V5LokH07y2SRHJPlGksfVWge6x0xKcn2SJyW5Lcm/DhnOK2utS4cZ47VJvltrffOgbQNJPlFrfeOgbR9J8qJa656llPlJ9k/y20Gn+nSt9dJSyn2Drj0pSV+SV9RabyqlLEzyxl
z0op+yQ5J8nUJNOSXJPkvYNez+FJ/ibJ79Vaf9Xd9t4kL0zyjF
6u62RUleXmv9xYNnYNv0mf93ZeZ9c16WrliS3afNzrw5p+WwvQ8f72EBAACN2+JR3HVvkr8ppTxvbfANcXQ6sfvmJK9Nkl
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
V+o/v4u0k+VkrZOcnOSX455PiHvH26e0v0/CT3DQnedM+1/+AN3dXhP
XfVWSm0oph6YT1sfnd1GcWus/l1L+b5K/GuE1JknWrBnI8uV3j7zjVrD7tNlZsuLmYbdvK2Nkw2bOnGqeepS5623mr3eZu95m/nqXuetdYzV3s2ZNH9V+Y
t07XWLyWp6X5uuJTyB0n6aq3PqrW+oNb6J0luSPLnG3HaS5K8Ip0w/tuNHNJRSQ7tXvsFSeZm0C3e3c8/X5Pk4+msIm+U7i3RxyR5SSnlkCFPfznJC0opj0/WfUnYuUn2TeeLtH5Qa/3T7tieluSRpZQ/HHKOed1999rYsY2neXNOy9T+9f/mZ0
lMybc9o4jQgAAKBja/xIpv+TZFX390cn+fSQ5z+ZQV9INZJa60/T+ebmn9Ra7xj01E6llIVDfj197ZOllP2TTKi1/tegYxYkeVYpZY9B265I5wu8rh7m8ucMOf+DPhRba12VTnxfUErZftD2O9P5DPMnu7daL0ryo3QCfLj35ZIMeV9qrfckeV2SHYYZ2z
sL0Pz8dfeFFmT9sjEzIhs6ftkXMPvMCXbAEAAONuwsDAcF8OTa+7
41A9vS7SNuZ+ld5q53mbveZv56l7n
eavd5m73jWGt0
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
WuKqX8IskTaq33dI/9WJKn11qfPOh8C5P8Z631rd3Hj0jys1
nlu9YLOeAAAgAElEQVTtRcEwFiy+KicunJtVq1clSZasuDknLpybJDls78PHc2gAADBqVoq3vFcl+WySl3cfvy3J12utB9Van5FkRZI3Dj2olDI1ybOS/LSUcuCQp19RSnn22A0ZNt5Zi05fF8R
Vq9KmctOn2cRgQAABvPSvEW1I3ZG9JZGf7bJPOT3JrkZaWUnyf5bpKTkwwMc/jhSb6R5B+THJ9k4aDnTkhycSnlj5KsHs1Y+vomZObMqZvyMsZEX9/EbWo8jN6G5m7piiXD7r90xRJzvY3w5663m
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
d8by4EBAADAWBvtSvHFST6VZFKSf05y/piNCAAAALaS0UbxlF
N5MM1FprknvGcEwAAACwVYw2iu8ppTw/SV8pZU5EMQAAAA8Do43iY5K8LskuSU5OctyYjQgAAAC2ktFG8aokl9Za90myMMmyMRsRAAAAbCWjjeLPJtmu+/vfJvnbsRkOAAAAbD2jjeLta61fTpJa65VJpo7dkAAAAGDrGNXPKU5yXynleUkWJXlakgfGbkgAAACwdYx2pfioJG9O8v0kb0py7JiNCAAAALaSUa0U11p/nuQv1j4upTxqzEYEAAAAW8mooriUckaSNyaZnM7niRcn2WcMxwUAAABj
S3Tx+aZHaSK5I8McnSMRsRAAAAbCWjjeJf11rvTTK9eyv15DEcEwAAAGwVo43iJaWU1ydZWUp5f5IdxnBMAAAAsFU85GeKSyn9SV6U5MokNyS5Oslb0/lMMQAAAPS0kb5o64okq5PsluTzSW5K50cynT/G4wIAAIAxN1IUP77W+pRSyuQkP0xyb5I
X+dOyHBgAAAGNrpM8U35kktdb7uvseJIgBAAB4uBjtF20lya211t+O2UgAAABgKxvp9ul9SilXJpkw6PdJkl
EWM6MgAAABhjI0Xx4YN+f9FYDgQAAAC2toeM4l
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
8ppfwiyX8nWZPOXzT8JsmRtda7uuc6Jclbkzy21npPd9v8JDNqrS8ddM1butdaN55SysQkpyY5uHv+gSRvqbVeN0ZvBwAAD2HB4qty1qLTs3TFkuw+bXbmzTkth+19+HgPC9hEVopH73VJbqm1HlRrfVaS7yR5z6DnD6q1/mmt9dlJru/uv9arknw2ycuzvmeVUl49wnVPSbJLkmfXWg/sPv6HUsqkTX8pAABsigWLr8qJC+dmyYqbM5CBLFlxc05cODcLFl813kMDNpEoHr1bkxxUSjm0lDIjyQVJThq6UyllQpKZSVZ0Hx+Y5IYkFyV585Dd35Hk9FLK7Ie47jFJzqi1PpAktdYfJHlqrfX+zXs5AABsrLMWnZ5Vq1ett23V6lU5a9Hp4zQiYHO5ffp3nlNKWTjo8eMyaCW41rqglDKQ5A1J5ie5Lsnc7j+T5J9KKWtv
5+ksu7249KckmttZZS7i2lHFB
V73uaVJ3p3k0iTP38C4ptZalw3eUGv9zUgvpq9vQmbOnDrSbltNX9/EbWo8jJ65613m
eZv95l7n
SPO3dMWSDW437+PLn73eNd5zJ4p/55vDfKY4gx4/Pck3aq1/X0rpS/LqdOL4j7q7HLT288KDjtkxyQuT7FpKmZtkhyTHJ1kbxam1XlFKeUkp5bgNjGtZKWVGrfXOQed9SXcsd27gmKxZM5Dly+8e8UVvLTNnTt2mxsPombveZe56m/nrXeaut400f7tPm50lK24edrt5H1/+7PWusZq7WbOmj2o/t0+P3iuSnJAktdY1SX6c5N4RjnlVkku7n0N+QZID0rkFe9aQ/Y5LcnKS4WbtsiSndW/LTinlGUnOTXLPMPsCADCG5s05LVP6p6y3bU
lMybc9o4jQjYXKJ49OYleXwp5dpSyneTnJ3OrdQP5agkn177oNZ69/9v7/6DLa
Oo6/LrsmS0tuPxAnIXEy3v2YIslRSrMtE03HcmKGHIsyS9IxB6XMhIyYZMYfRSn+qDQtrSZIsqkmFcpIMzYMzX6QH/LHFNho/ghpZdNluf1xzrUr3csu7F7O+fJ+PGaYPfd7vufez9n3fHf3eb7fc0hyeZKnrd9pjPHxJOdm9qnWt/fSzOL76qp6Z5IXJvneMcbn7uoTAQDgrjnj5DNz8e5LcsLOE7OSlZyw88RcvPsSnz4NE7ayurq66DWwBfbvP7C6TJePuJxlusxuusxu2sxvusxu2sxvusxuu
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
kXPThQfnvcm+dqqWknyyCTnJfnzJN+d5JuSvDXJ05O8oapumT/m
yP+4qqWrt8+sAY41EHe8CBA6u56aZbD
3WbXrmOWaj0cOrObLrObNvObLrObNvNbHvffeUJu3HvDhts3mpHZTddWze644449pP180NZhGGPcltnl0Y9N8tExxmeTvCXJw5M8IskV811/eIyxe35Z9Ol34Uedvvb4QwliAACYuvNPuyA7tu/4gm07tu/I+addsKAVcU8lig/flZmdIX7L/Ou/zuzS6aPGGJ9a2KoAAGDCzjj5zFy8+5KcsPPErGQlJ+w8MRfvvsT7iTniXD59+K5M8pokZyXJGONzVXVTkr8/gj9j/eXTSfKyMcabj+D3BwCApXPGyWeKYLbcyurq6qLXwBbYv
A6jK9p8J7PKbL7KbL7KbN/KbL7KbN/KbL7KZrC99TfG2ShxxsP5dPAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLZEMQAAAG2JYgAAANoSxQAAALQligEAAGhLFAMAANCWKAYAAKAtUQwAAEBbohgAAIC2RDEAAABtiWIAAADaEsUAAAC0JYoBAABoSxQDAADQligGAACgLVEMAABAW6IYAACAtkQxAAAAbW1f9AKmrKp2J7ksyXVJVpLcO8kzkpyT5PfHGG/d4DFnJnl9kq8ZY/zHuu1PnD9uJcmOJC8dY7ypqp6S5GvHGD873++cJD+Q5PFjjP/aumcHAACwucuvvywX7bkwH9l7Y+6/84Scf9oFOePkMxe9rDtNFB++t48xnpQkVXV6kl9M8ok72P9pSV6e5OwkvzB/3LcleU5mobu3qr48yZ6qum79A6vquUkek+TRY4zPHOknAgAAcCguv/6ynHvVs7Lv1n1Jkhv33pBzr3pWkkwujF0+fWR9aZL/3OzOqnpgki9L8uIkZ1XVveZ3PS3Jr44x9ibJGOOTSR6a5F/WPfb8JN+VWTgLYgAAYGEu2nPh54N4zb5b9+WiPRcuaEV3nTPFh++7quqqzC6dPiXJE5M8eZN9fyzJ68YYN1XV1Um+P8mlSb4yyYfW77h2aXRVJckPJvnXzKJ75VAWtW3bSnbtOubOPpcts23bUUu1Hg6d2U2X2U2b+U2X2U2b+U2X2d29PrL3xk2339k5LHp2ovjw
98upJcneTK2+9UVduS/FCSD1fVEzI7Y/yTmUXxvyU5Mcn71u3/8CQfm3/53sxi+yVJXpHkxw+2qAMHVnPTTbfc9Wd1hO3adcxSrYdDZ3bTZXbTZn7TZXbTZn7TZXZ3
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
Qk/xPH3iRsMr97ZcmOPWeK2UpPTHL0GONbk/xskl9e8HrYQFUdnWRljLF7/t+PJvm1JE9O8ogkD5v/o908l0hV/UyS1yY5er7p4iQ/N8b49iQrSb6vqk5N8h1JHpbkSUleudm+d+fau9tgdt+S5OJ1x+ClZreUfijJJ+e/949N8oo47qZko/k59qbhCUkyxnh4kp9LclEce1Oy0fyW7tgTxWylRyR5a5KMMfYkechil8MmTklyTFVdUVVvr6pHJrn3GOODY4zVJG9L8t0xz2XzwSTfv+7
0nyV/P
8n/zeyKMcbqGOPfk2yvquM22Ze7z0aze3xVvaOqfrOqjo3ZLaM/SPKC+e2VzM5kOO6mY7P5OfaW3Bjjj5KcPf/yAUluimNvMu5gfkt17IlittKXJPn0uq8PVJVL9pfPLUl+KcljMruk5fXzbWv+O8l9Yp5LZYxxeZL96zatzF/ESDaf2dr2jfbl
LB7K5J8twxxiOTfCjJBTG7pTPG2DvG+O/5P97elNkZD8fdRGwyP8feRIwxbq2q305ySZLfjWNvUjaY39Ide6KYrXRzkmPXfX3UGOPWRS2GTV2f5Hfmr8xdn9kfSF+27v5jM3tVzzyX2
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
aL5vvdLcrogBmCriWIAYFNjjE8meXaS387G/25Yf2n1e+a/3pTkuvnt/0py9Pz2+8YYnx5jHEhyTWZnkb8xyXlVdVWSn8/sLHKSfHiM8bkj9TwAYDOiGAC4Q2OMP0kyMrtE+n5J7ltV26pqV5IHrtt19SDf6uuqamdVbU/ysCT/nOT9SZ43P1P8E0n+YL7vbUfuGQDA5rynGAA4FM9O8qjM3ht8ZZJ3J/lgkg/cie/xqSSXJjkuyaVjjOuq6qeTvLqqjs7sfcXnHNFVA8BBrKyuHuxFXQAAALhncvk0AAAAbYliAAAA2hLFAAAAtCWKAQAAaEsUAwAA0JYoBgAAoC1RDAAAQFuiGAAAgLb+Fw6pa8Uy+R6EAAAAAElFTkSuQmCC\n",
"text/plain": [
"

"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"---------------------------------------\n",
"Aggregated count of Violations by GENDER\n",
" Gender Count\n",
"0 M 7065\n",
"1 F 2932\n",
"2 U 3\n"
]
},
{
"data": {
"image/png":...