Add file

Feature Importance.ipynb

@@ -0,0 +1,214 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "root\n",
+      " |-- A: integer (nullable = true)\n",
+      " |-- B: integer (nullable = true)\n",
+      " |-- C: double (nullable = true)\n",
+      " |-- D: integer (nullable = true)\n",
+      " |-- Spoiled: double (nullable = true)\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pyspark.sql import SparkSession\n",
+    "spark = SparkSession.builder.appName('dog_food_tree').getOrCreate()\n",
+    "df = spark.read.csv('dog_food.csv', inferSchema=True, header=True)\n",
+    "df.printSchema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+---+---+----+---+-------+\n",
+      "|  A|  B|   C|  D|Spoiled|\n",
+      "+---+---+----+---+-------+\n",
+      "|  4|  2|12.0|  3|    1.0|\n",
+      "|  5|  6|12.0|  7|    1.0|\n",
+      "+---+---+----+---+-------+\n",
+      "only showing top 2 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.show(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pyspark.ml.feature import VectorAssembler\n",
+    "\n",
+    "assembler = VectorAssembler(inputCols = ['A', 'B', 'C', 'D'], outputCol = 'features')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output = assembler.transform(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+---+---+----+---+-------+------------------+\n",
+      "|  A|  B|   C|  D|Spoiled|          features|\n",
+      "+---+---+----+---+-------+------------------+\n",
+      "|  4|  2|12.0|  3|    1.0|[4.0,2.0,12.0,3.0]|\n",
+      "|  5|  6|12.0|  7|    1.0|[5.0,6.0,12.0,7.0]|\n",
+      "|  6|  2|13.0|  6|    1.0|[6.0,2.0,13.0,6.0]|\n",
+      "+---+---+----+---+-------+------------------+\n",
+      "only showing top 3 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "output.show(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pyspark.ml.classification import RandomForestClassifier\n",
+    "\n",
+    "rf = RandomForestClassifier(labelCol = 'Spoiled', featuresCol = 'features')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "final_df = output.select('features', 'Spoiled')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+------------------+-------+\n",
+      "|          features|Spoiled|\n",
+      "+------------------+-------+\n",
+      "|[4.0,2.0,12.0,3.0]|    1.0|\n",
+      "|[5.0,6.0,12.0,7.0]|    1.0|\n",
+      "|[6.0,2.0,13.0,6.0]|    1.0|\n",
+      "+------------------+-------+\n",
+      "only showing top 3 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "final_df.show(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rf_model = rf.fit(final_df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Row(features=DenseVector([4.0, 2.0, 12.0, 3.0]), Spoiled=1.0)]"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "final_df.take(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "SparseVector(4, {0: 0.0212, 1: 0.0166, 2: 0.9373, 3: 0.025})"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rf_model.featureImportances"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "conda_python3",
+   "language": "python",
+   "name": "conda_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": "3.6.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}