{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e5905a69",
   "metadata": {},
   "source": [
    "# CSE6242 - HW3 - Q1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09289981",
   "metadata": {},
   "source": [
    "Pyspark Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "139318cb",
   "metadata": {},
   "outputs": [],
   "source": [
    "### DO NOT MODIFY THIS CELL ###\n",
    "import pyspark\n",
    "from pyspark.sql import SQLContext\n",
    "from pyspark.sql.functions import hour, when, col, date_format, to_timestamp, round, coalesce\n",
    "from pyspark.sql.functions import *"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3fd9e0f8",
   "metadata": {},
   "source": [
    "Initialize PySpark Context"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b0c18c6c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting default log level to \"WARN\".\n",
      "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
      "23/10/18 14:58:22 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n",
      "23/10/18 14:58:22 WARN Utils: Service 'SparkUI' could not bind on port 4040. Attempting port 4041.\n",
      "23/10/18 14:58:22 WARN Utils: Service 'SparkUI' could not bind on port 4041. Attempting port 4042.\n",
      "23/10/18 14:58:22 WARN Utils: Service 'SparkUI' could not bind on port 4042. Attempting port 4043.\n",
      "/usr/local/lib/python3.9/dist-packages/pyspark/sql/context.py:113: FutureWarning: Deprecated in 3.0.0. Use SparkSession.builder.getOrCreate() instead.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "### DO NOT MODIFY THIS CELL ###\n",
    "sc = pyspark.SparkContext(appName=\"HW3-Q1\")\n",
    "sqlContext = SQLContext(sc)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d68ae314",
   "metadata": {},
   "source": [
    "Define function for loading data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7e5bbdda",
   "metadata": {},
   "outputs": [],
   "source": [
    "### DO NOT MODIFY THIS CELL ###\n",
    "def load_data():\n",
    "    df = sqlContext.read.option(\"header\",True) \\\n",
    "     .csv(\"yellow_tripdata_2019-01_short.csv\")\n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d52409d",
   "metadata": {},
   "source": [
    "### Q1.a"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e43f6e00",
   "metadata": {},
   "source": [
    "Perform data casting to clean incoming dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "11f801b4",
   "metadata": {},
   "outputs": [],
   "source": [
    "def clean_data(df):\n",
    "    '''\n",
    "    input: df a dataframe\n",
    "    output: df a dataframe with the all the original columns\n",
    "    '''\n",
    "    \n",
    "    # START YOUR CODE HERE ---------\n",
    "    from pyspark.sql.types import StructField, StructType, IntegerType, TimestampType, FloatType, StringType\n",
    "\n",
    "    df = df.withColumn(\"passenger_count\", df[\"passenger_count\"].cast(IntegerType()))\n",
    "    df = df.withColumn(\"total_amount\", df[\"total_amount\"].cast(FloatType()))\n",
    "    df = df.withColumn(\"tip_amount\", df[\"tip_amount\"].cast(FloatType()))\n",
    "    df = df.withColumn(\"trip_distance\", df[\"trip_distance\"].cast(FloatType()))\n",
    "    df = df.withColumn(\"fare_amount\", df[\"fare_amount\"].cast(FloatType()))\n",
    "    df = df.withColumn(\"tpep_pickup_datetime\", df[\"tpep_pickup_datetime\"].cast(TimestampType()))\n",
    "    df = df.withColumn(\"tpep_dropoff_datetime\", df[\"tpep_dropoff_datetime\"].cast(TimestampType()))\n",
    "\n",
    "    # END YOUR CODE HERE -----------\n",
    "    \n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4f565d0",
   "metadata": {},
   "source": [
    "### Q1.b"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "72b4f712",
   "metadata": {},
   "source": [
    "Find rate per person for based on how many passengers travel between pickup and dropoff locations. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4e115152",
   "metadata": {},
   "outputs": [],
   "source": [
    "def common_pair(df):\n",
    "    '''\n",
    "    input: df a dataframe\n",
    "    output: df a dataframe with following columns:\n",
    "            - PULocationID\n",
    "            - DOLocationID\n",
    "            - passenger_count\n",
    "            - per_person_rate\n",
    "            \n",
    "    per_person_rate is the total_amount per person for a given pair.\n",
    "    \n",
    "    '''\n",
    "    \n",
    "    # START YOUR CODE HERE ---------\n",
    "    from pyspark.sql import Window\n",
    "\n",
    "    partition_cols = ['PULocationID','DOLocationID']\n",
    "\n",
    "    group_by_result = df.groupBy(partition_cols).count()\n",
    "    # group_by_result.show()\n",
    "\n",
    "    # Filter out any trips that have the same pick-up and drop-off location. \n",
    "    df_temp = df.filter((df.PULocationID != df.DOLocationID))\n",
    "    # group_by_result_difference_location.show()\n",
    "\n",
    "    # # [4 pts] You will be modifying the function common_pair. \n",
    "    # # Return the top 10 pickup-dropoff location pairs that have the highest number of total passengers who have traveled between them. \n",
    "    # # Sort the location pairs by total passengers. \n",
    "    df_temp = df_temp.withColumn(\"passenger_count\", sum(\"passenger_count\").over(Window.partitionBy(*partition_cols)))\n",
    "    \n",
    "    # # For each location pair, also compute \n",
    "    #     # the average amount per passenger over all trips (name this per_person_rate), utilizing total_amount.\n",
    "    df_temp = df_temp.withColumn(\"total_amount_partition\", sum(\"total_amount\").over(Window.partitionBy(*partition_cols)))\n",
    "    df_temp = df_temp.withColumn(\"per_person_rate\",col(\"total_amount_partition\")/col(\"passenger_count\"))\n",
    "    \n",
    "    # # For pairs with the same total passengers, \n",
    "    #     # sort them in descending order of per_person_rate.\n",
    "    # # Rename the column for total passengers to passenger_count. \n",
    "    df_temp = df_temp.select(['PULocationID','DOLocationID','passenger_count','per_person_rate']).distinct()\n",
    "    df_joined  = group_by_result.join(df_temp, partition_cols)\n",
    "    df_joined = df_joined.orderBy(['passenger_count','per_person_rate'], ascending=False).limit(10)\n",
    "    df_output = df_joined.drop('count')\n",
    "    # END YOUR CODE HERE -----------\n",
    "    \n",
    "    return df_output"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "127574ab",
   "metadata": {},
   "source": [
    "### Q1.c"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36a8fd27",
   "metadata": {},
   "source": [
    "Find trips which trip distances generate the highest tip percentage."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "376c981c",
   "metadata": {},
   "outputs": [],
   "source": [
    "def distance_with_most_tip(df):\n",
    "    '''\n",
    "    input: df a dataframe\n",
    "    output: df a dataframe with following columns:\n",
    "            - trip_distance\n",
    "            - tip_percent\n",
    "            \n",
    "    trip_percent is the percent of tip out of fare_amount\n",
    "    \n",
    "    '''\n",
    "    \n",
    "    # START YOUR CODE HERE ---------\n",
    "    \n",
    "    # END YOUR CODE HERE -----------\n",
    "    \n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f0172fe6",
   "metadata": {},
   "source": [
    "### Q1.d"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4613c906",
   "metadata": {},
   "source": [
    "Determine the average speed at different times of day."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "abff9e24",
   "metadata": {},
   "outputs": [],
   "source": [
    "def time_with_most_traffic(df):\n",
    "    '''\n",
    "    input: df a dataframe\n",
    "    output: df a dataframe with following columns:\n",
    "            - time_of_day\n",
    "            - am_avg_speed\n",
    "            - pm_avg_speed\n",
    "            \n",
    "    trip_percent is the percent of tip out of fare_amount\n",
    "    \n",
    "    '''\n",
    "    \n",
    "    # START YOUR CODE HERE ---------\n",
    "\n",
    "    # END YOUR CODE HERE -----------\n",
    "    \n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "34cbd7b9",
   "metadata": {},
   "source": [
    "### The below cells are for you to investigate your solutions and will not be graded\n",
    "## Ensure they are commented out prior to submitting to Gradescope to avoid errors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "bf9abefb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------+------------+---------------+------------------+\n",
      "|PULocationID|DOLocationID|passenger_count|   per_person_rate|\n",
      "+------------+------------+---------------+------------------+\n",
      "|         239|         238|             62|  4.26274198870505|\n",
      "|         237|         236|             60| 4.482500068346659|\n",
      "|         263|         141|             52|3.4190384974846473|\n",
      "|         161|         236|             42| 5.368571440378825|\n",
      "|         148|          79|             42| 4.711904752822149|\n",
      "|         142|         238|             39|  5.05487182812813|\n",
      "|         141|         236|             37| 4.355675723101641|\n",
      "|         239|         143|             37| 4.252162224537617|\n",
      "|         239|         142|             35| 3.817714350564139|\n",
      "|          79|         170|             34| 6.394705884596881|\n",
      "+------------+------------+---------------+------------------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# df = load_data()\n",
    "# df = clean_data(df)\n",
    "# common_pair(df).show()\n",
    "# distance_with_most_tip(df).show()\n",
    "# time_with_most_traffic(df).show()"
   ]
  }
 ],
 "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": "3.9.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}