Update-20180101

Intro-DataAnalysis/L1-DataAnalysisProcess/assessing_quiz.ipynb

@@ -0,0 +1,208 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "# Assessing and Building Intuition Quiz\n",
+    "Use the space below to explore `census_income_data.csv` to answer the quiz questions below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import pandas\n",
+    "import pandas as pd\n",
+    "# Load census income data\n",
+    "df = pd.read_csv('census_income_data.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(32561, 15)"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Work to answer the quiz questions\n",
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 32561 entries, 0 to 32560\n",
+      "Data columns (total 15 columns):\n",
+      "age               32561 non-null int64\n",
+      "workclass         30725 non-null object\n",
+      "fnlwgt            32561 non-null int64\n",
+      "education         32561 non-null object\n",
+      "education-num     32561 non-null int64\n",
+      "marital-status    32561 non-null object\n",
+      "occupation        30718 non-null object\n",
+      "relationship      32561 non-null object\n",
+      "race              32561 non-null object\n",
+      "sex               32561 non-null object\n",
+      "capital-gain      32561 non-null int64\n",
+      "capital-loss      32561 non-null int64\n",
+      "hours-per-week    32561 non-null int64\n",
+      "native-country    31978 non-null object\n",
+      "income            32561 non-null object\n",
+      "dtypes: int64(6), object(9)\n",
+      "memory usage: 3.7+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "age                  0\n",
+       "workclass         1836\n",
+       "fnlwgt               0\n",
+       "education            0\n",
+       "education-num        0\n",
+       "marital-status       0\n",
+       "occupation        1843\n",
+       "relationship         0\n",
+       "race                 0\n",
+       "sex                  0\n",
+       "capital-gain         0\n",
+       "capital-loss         0\n",
+       "hours-per-week       0\n",
+       "native-country     583\n",
+       "income               0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()\n",
+    "#计算每列缺失值的数量"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "16"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(df['education'].unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "39.0"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "round(df['age'].mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count    32561.000000\n",
+       "mean        40.437456\n",
+       "std         12.347429\n",
+       "min          1.000000\n",
+       "25%         40.000000\n",
+       "50%         40.000000\n",
+       "75%         45.000000\n",
+       "max         99.000000\n",
+       "Name: hours-per-week, dtype: float64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['hours-per-week'].describe()"
+   ]
+  }
+ ],
+ "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
+}