Update-20180105

xueqingwong · Jan 5, 2018 · c975e88 · c975e88
1 parent 04ba61c
commit c975e88
Show file tree

Hide file tree

Showing 36 changed files with 70,868 additions and 0 deletions.
diff --git a/Intro-DataAnalysis/L3-CaseStudy2/GreenVehicleGuideDocumentation.pdf b/Intro-DataAnalysis/L3-CaseStudy2/GreenVehicleGuideDocumentation.pdf
diff --git a/Intro-DataAnalysis/L3-CaseStudy2/all_alpha_08.csv b/Intro-DataAnalysis/L3-CaseStudy2/all_alpha_08.csv
diff --git a/Intro-DataAnalysis/L3-CaseStudy2/all_alpha_18.csv b/Intro-DataAnalysis/L3-CaseStudy2/all_alpha_18.csv
diff --git a/Intro-DataAnalysis/L3-CaseStudy2/assessing.html b/Intro-DataAnalysis/L3-CaseStudy2/assessing.html
diff --git a/Intro-DataAnalysis/L3-CaseStudy2/assessing.ipynb b/Intro-DataAnalysis/L3-CaseStudy2/assessing.ipynb
@@ -0,0 +1,277 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "# Assessing\n",
+    "Use the space below to explore `all_alpha_08.csv` and `all_alpha_18.csv` to answer the quiz questions below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "df_08 = pd.read_csv('all_alpha_08.csv')\n",
+    "df_18 = pd.read_csv('all_alpha_18.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(2404, 18)\n",
+      "25\n",
+      "199\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_08.shape)\n",
+    "print(df_08.duplicated().sum())\n",
+    "print(sum(df_08.isnull().sum(axis = 1) > 0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 2404 entries, 0 to 2403\n",
+      "Data columns (total 18 columns):\n",
+      "Model                   2404 non-null object\n",
+      "Displ                   2404 non-null float64\n",
+      "Cyl                     2205 non-null object\n",
+      "Trans                   2205 non-null object\n",
+      "Drive                   2311 non-null object\n",
+      "Fuel                    2404 non-null object\n",
+      "Sales Area              2404 non-null object\n",
+      "Stnd                    2404 non-null object\n",
+      "Underhood ID            2404 non-null object\n",
+      "Veh Class               2404 non-null object\n",
+      "Air Pollution Score     2404 non-null object\n",
+      "FE Calc Appr            2205 non-null object\n",
+      "City MPG                2205 non-null object\n",
+      "Hwy MPG                 2205 non-null object\n",
+      "Cmb MPG                 2205 non-null object\n",
+      "Unadj Cmb MPG           2205 non-null float64\n",
+      "Greenhouse Gas Score    2205 non-null object\n",
+      "SmartWay                2404 non-null object\n",
+      "dtypes: float64(2), object(16)\n",
+      "memory usage: 338.1+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_08.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(1611, 18)\n",
+      "0\n",
+      "2\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_18.shape)\n",
+    "print(df_18.duplicated().sum())\n",
+    "print(sum(df_18.isnull().sum(axis = 1) > 0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 1611 entries, 0 to 1610\n",
+      "Data columns (total 18 columns):\n",
+      "Model                   1611 non-null object\n",
+      "Displ                   1609 non-null float64\n",
+      "Cyl                     1609 non-null float64\n",
+      "Trans                   1611 non-null object\n",
+      "Drive                   1611 non-null object\n",
+      "Fuel                    1611 non-null object\n",
+      "Cert Region             1611 non-null object\n",
+      "Stnd                    1611 non-null object\n",
+      "Stnd Description        1611 non-null object\n",
+      "Underhood ID            1611 non-null object\n",
+      "Veh Class               1611 non-null object\n",
+      "Air Pollution Score     1611 non-null int64\n",
+      "City MPG                1611 non-null object\n",
+      "Hwy MPG                 1611 non-null object\n",
+      "Cmb MPG                 1611 non-null object\n",
+      "Greenhouse Gas Score    1611 non-null int64\n",
+      "SmartWay                1611 non-null object\n",
+      "Comb CO2                1611 non-null object\n",
+      "dtypes: float64(2), int64(2), object(14)\n",
+      "memory usage: 226.6+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_18.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model : 436\n",
+      "Displ : 47\n",
+      "Cyl : 8\n",
+      "Trans : 14\n",
+      "Drive : 2\n",
+      "Fuel : 5\n",
+      "Sales Area : 3\n",
+      "Stnd : 12\n",
+      "Underhood ID : 343\n",
+      "Veh Class : 9\n",
+      "Air Pollution Score : 13\n",
+      "FE Calc Appr : 2\n",
+      "City MPG : 39\n",
+      "Hwy MPG : 43\n",
+      "Cmb MPG : 38\n",
+      "Unadj Cmb MPG : 721\n",
+      "Greenhouse Gas Score : 20\n",
+      "SmartWay : 2\n"
+     ]
+    }
+   ],
+   "source": [
+    "for col in df_08.columns:\n",
+    "    print('{} : {}'.format(col, len(df_08[col].dropna().unique())))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model : 367\n",
+      "Displ : 36\n",
+      "Cyl : 7\n",
+      "Trans : 26\n",
+      "Drive : 2\n",
+      "Fuel : 5\n",
+      "Cert Region : 2\n",
+      "Stnd : 19\n",
+      "Stnd Description : 19\n",
+      "Underhood ID : 230\n",
+      "Veh Class : 9\n",
+      "Air Pollution Score : 6\n",
+      "City MPG : 58\n",
+      "Hwy MPG : 62\n",
+      "Cmb MPG : 57\n",
+      "Greenhouse Gas Score : 10\n",
+      "SmartWay : 3\n",
+      "Comb CO2 : 299\n"
+     ]
+    }
+   ],
+   "source": [
+    "for col in df_18.columns:\n",
+    "    print('{} : {}'.format(col, len(df_18[col].dropna().unique())))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['(6 cyl)' '(4 cyl)' '(12 cyl)' '(8 cyl)' '(10 cyl)' '(16 cyl)' '(5 cyl)'\n",
+      " nan '(2 cyl)']\n",
+      "[  6.   4.   5.  12.  16.   8.  nan   3.]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_08['Cyl'].unique())\n",
+    "print(df_18['Cyl'].unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['Gasoline' 'ethanol/gas' 'ethanol' 'diesel' 'CNG']\n",
+      "['Gasoline' 'Gasoline/Electricity' 'Diesel' 'Ethanol/Gas' 'Electricity']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_08['Fuel'].unique())\n",
+    "print(df_18['Fuel'].unique())"
+   ]
+  }
+ ],
+ "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": "3.6.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}