Predicting Border Crossing Entry Data using various Machine learning techniques
Create New

Predicting Border Crossing Entry Data using various Machine learning techniques

Project period

10/20/2019 - 11/18/2019

Views

63

0



Predicting Border Crossing Entry Data using various Machine learning techniques
Predicting Border Crossing Entry Data using various Machine learning techniques

Driving is considered to be one of the most difficult tasks of the day. All the drivers, it may be men or women will definitely experience tiredness or frustration whenever they have to drive through long traffic conditions. Nowadays, Road accidents play a major problem in public health and development. Road injuries and accidents are predicted to increase if road safety is not addressed adequately.  Also, road traffic is the most complicated daily need. According to a report, more than 150,000 people are killed each year in traffic accidents, leading to around 400 deaths per day. Studies have released that road accidents and death- laceration ratio will keep on increasing. Designing and controlling traffic by advanced systems are available in order to fulfill the vital traffic needs. Assumption on the risks in traffic and the law and regulations will tend to reduce the road accidents.

Why: Problem statement

Nowadays traffic has been considered a difficult structure in designing and managing by the reason of increasing large number of vehicles. This situation has increased road accidents. Road accidents have influenced public health and country economy and many studies have been done to obtain a solution. Arising the need of accession to information from this large calibrated data obtained the cornerstone of the data mining. In this project, we will be using the most advanced machine learning classification techniques for road accident prediction by data mining.

There are a number of problems with trending practices for prevention of the accidents occurring in all areas. We will use few databases that are readily available officially by many sectors and government websites. The collected data will be analyzed, integrated and grouped together based on different constraints using the best-suited algorithm. This analysis will be useful to examine and identify the mistakes and the possible reasons for road accidents. It will also be helpful while construction roads and bridges. These predictions made will be very much helpful to plan and manage such problems.

How: Solution description

Data Collection:

I collected the US border crossing entry data dataset for this problem. It is a multivariate dataset containing attributes that are: port name, state, portcode, border, measure, value and location. Here, we are not using any data cleaning process since there are no missing values.

The Block Diagram has been shown below:

 

Machine Learning Models:

First, I used the k-nearest-neighbor algorithm. Often abbreviated knn, it is an approach to data classification that estimates a data point is to be a member of one group or the other depending on the group the data points nearest. While training the model, I got the accuracy of 0.7894.

Then, I used the decision-tree classifier algorithm. It is a predictive modeling tool that has applications spanning a number of different areas, and decision trees are constructed via an algorithmic approach that identifies ways to split a data set based on different conditions. While training the model, I got the accuracy of 1.0.

How is it different from competition

Deep learning is the best method used for transportation or traffic-related predictions. But the existing projects fall short in different angles such as the use of the information, insufficient depth of machine learning tools, etc.

To analyze the raw data manually and predict a solution for traffic congestions form a tough process. But machine learning technology automatically detects the patterns or information from the available data, using the data mining algorithms. when using Data mining algorithms. Decision trees are the best-used approach for representing the data. Using Decision trees, data can be clearly understood in the most clear form of data. Every algorithm has a unique decision tree from the input data.

After using machine-learning models, I was able to conclude that the decision tree classifier algorithm is the best classification algorithm for the border crossing entry dataset.

Who are your customers

Traffic Controllers and Traffic Police are my Customers.

Project Phases and Schedule

Phase 1: Data Collection

Phase 2: Data Cleaning

Phase 3: Data Analysis 

Phase 4: Prediction using machine learning techniques.

Resources Required

Software Used:

1. Anaconda tool

2. Python 3.7

3. Text editor - Jupyter notebook

Download:
Project Code Code copy
/* Your file Name : bordercrossing.ipynb */
/* Your coding Language : python */
/* Your code snippet start here */
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data=pd.read_csv('Book1.csv',index_col='portname')\n",
    "# changing the column names for convenience\n",
    "data.columns = list(map(str.lower, data.columns.values.tolist()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "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>state</th>\n",
       "      <th>portcode</th>\n",
       "      <th>border</th>\n",
       "      <th>measure</th>\n",
       "      <th>value</th>\n",
       "      <th>location</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>portname</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Calexico East</th>\n",
       "      <td>California</td>\n",
       "      <td>2507</td>\n",
       "      <td>US-Mexico Border</td>\n",
       "      <td>Trucks</td>\n",
       "      <td>34447</td>\n",
       "      <td>POINT (-115.48433000000001 32.67524)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Van Buren</th>\n",
       "      <td>Maine</td>\n",
       "      <td>108</td>\n",
       "      <td>US-Canada Border</td>\n",
       "      <td>Rail Containers Full</td>\n",
       "      <td>428</td>\n",
       "      <td>POINT (-67.94271 47.16207)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Otay Mesa</th>\n",
       "      <td>California</td>\n",
       "      <td>2506</td>\n",
       "      <td>US-Mexico Border</td>\n",
       "      <td>Trucks</td>\n",
       "      <td>81217</td>\n",
       "      <td>POINT (-117.05333 32.57333)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nogales</th>\n",
       "      <td>Arizona</td>\n",
       "      <td>2604</td>\n",
       "      <td>US-Mexico Border</td>\n",
       "      <td>Trains</td>\n",
       "      <td>62</td>\n",
       "      <td>POINT (-110.93361 31.340279999999996)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Trout River</th>\n",
       "      <td>New York</td>\n",
       "      <td>715</td>\n",
       "      <td>US-Canada Border</td>\n",
       "      <td>Personal Vehicle Passengers</td>\n",
       "      <td>16377</td>\n",
       "      <td>POINT (-73.44253 44.990010000000005)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    state  portcode            border  \\\n",
       "portname                                                \n",
       "Calexico East  California      2507  US-Mexico Border   \n",
       "Van Buren           Maine       108  US-Canada Border   \n",
       "Otay Mesa      California      2506  US-Mexico Border   \n",
       "Nogales           Arizona      2604  US-Mexico Border   \n",
       "Trout River      New York       715  US-Canada Border   \n",
       "\n",
       "                                   measure  value  \\\n",
       "portname                                            \n",
       "Calexico East                       Trucks  34447   \n",
       "Van Buren             Rail Containers Full    428   \n",
       "Otay Mesa                           Trucks  81217   \n",
       "Nogales                             Trains     62   \n",
       "Trout River    Personal Vehicle Passengers  16377   \n",
       "\n",
       "                                            location  \n",
       "portname                                              \n",
       "Calexico East   POINT (-115.48433000000001 32.67524)  \n",
       "Van Buren                 POINT (-67.94271 47.16207)  \n",
       "Otay Mesa                POINT (-117.05333 32.57333)  \n",
       "Nogales        POINT (-110.93361 31.340279999999996)  \n",
       "Trout River     POINT (-73.44253 44.990010000000005)  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1c52412a5f8>"
      ]
     },
     "execution_count": 4,
     "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": [
    "sb.boxplot(x='portcode', y='value', data=data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1c524a22710>"
      ]
     },
     "execution_count": 5,
     "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": [
    "sb.boxplot(x= 'portcode', y='border', data = data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1c524a66470>"
      ]
     },
     "execution_count": 6,
     "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": [
    "sb.boxplot(x= 'portcode', y= 'state', data = data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\hp\\Anaconda3\\lib\\site-packages\\seaborn\\axisgrid.py:230: UserWarning: The `size` paramter has been renamed to `height`; please update your code.\n",
      "  warnings.warn(msg, UserWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1c524b924a8>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 416x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.FacetGrid(data, hue='border', size=4).\\\n",
    "                   map(plt.scatter, 'portcode',\n",
    "                   'portcode').add_legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\hp\\Anaconda3\\lib\\site-packages\\seaborn\\axisgrid.py:230: UserWarning: The `size` paramter has been renamed to `height`; please update your code.\n",
      "  warnings.warn(msg, UserWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1c524c5acc0>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 416x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.FacetGrid(data, hue='border', size=4).\\\n",
    "                   map(plt.scatter, 'state',\n",
    "                   'state').add_legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\hp\\Anaconda3\\lib\\site-packages\\seaborn\\axisgrid.py:230: UserWarning: The `size` paramter has been renamed to `height`; please update your code.\n",
      "  warnings.warn(msg, UserWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1c524c32048>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 416x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.FacetGrid(data, hue='border', size=4).\\\n",
    "                   map(plt.scatter, 'measure',\n",
    "                   'measure').add_legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Accuracy 0.9017857142857143\n",
      "Testing Accuracy 0.7894736842105263\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "# Now we know which features are most likely to contribute to our model\n",
    "# so lets create a model and see the accuracy\n",
    "X_train, X_test, Y_train, Y_test = train_test_split(\n",
    "        data.loc[:, ['portcode', 'value']], \n",
    "        data.loc[:, 'border'])\n",
    "\n",
    "knn = KNeighborsClassifier(n_neighbors=2, p=2, metric='minkowski')\n",
    "knn.fit(X_train, Y_train)\n",
    "print (\"Training Accuracy {}\".format(knn.score(X_train, Y_train)))\n",
    "print (\"Testing Accuracy {}\".format(knn.score(X_test, Y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Accuracy 1.0\n",
      "Testing Accuracy 1.0\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "des=DecisionTreeClassifier()\n",
    "des.fit(X_train,Y_train)\n",
    "des.predict(X_test)\n",
    "print(\"Training Accuracy {}\".format(des.score(X_train,Y_train)))\n",
    "print(\"Testing Accuracy {}\".format(des.score(X_test,Y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}
View on Github
github_link

Comments

Leave a Comment

Post a Comment