Skip to content

Instantly share code, notes, and snippets.

@fenago

fenago/proj_2-3_exams.ipynb

Created October 21, 2024 13:18
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save fenago/eed1fa268b0a1310a1e32d27dc8ee4b0 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save fenago/eed1fa268b0a1310a1e32d27dc8ee4b0 to your computer and use it in GitHub Desktop.
Download ZIP
proj_2-3_exams.ipynb
Display the source blob
Display the rendered blob
Raw
proj_2-3_exams.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/fenago/eed1fa268b0a1310a1e32d27dc8ee4b0/proj_2-3_exams.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ua-Kno7iOlmT"
},
"source": [
"# Project 2-3: Analyze the exam data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "1ozOD-UrOlmX"
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qBYgK8t-OlmY"
},
"source": [
"## Tasks"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "wHzs4c6qOlmZ",
"outputId": "a7a068ba-3343-40c4-fd83-fc39165402c2"
},
"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>gender</th>\n",
" <th>race/ethnicity</th>\n",
" <th>parental level of education</th>\n",
" <th>lunch</th>\n",
" <th>test preparation course</th>\n",
" <th>math score</th>\n",
" <th>reading score</th>\n",
" <th>writing score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>bachelor's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>72</td>\n",
" <td>72</td>\n",
" <td>74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>female</td>\n",
" <td>group C</td>\n",
" <td>some college</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>69</td>\n",
" <td>90</td>\n",
" <td>88</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>master's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>90</td>\n",
" <td>95</td>\n",
" <td>93</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>male</td>\n",
" <td>group A</td>\n",
" <td>associate's degree</td>\n",
" <td>free/reduced</td>\n",
" <td>none</td>\n",
" <td>47</td>\n",
" <td>57</td>\n",
" <td>44</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>male</td>\n",
" <td>group C</td>\n",
" <td>some college</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>76</td>\n",
" <td>78</td>\n",
" <td>75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" gender race/ethnicity parental level of education lunch \\\n",
"0 female group B bachelor's degree standard \n",
"1 female group C some college standard \n",
"2 female group B master's degree standard \n",
"3 male group A associate's degree free/reduced \n",
"4 male group C some college standard \n",
"\n",
" test preparation course math score reading score writing score \n",
"0 none 72 72 74 \n",
"1 completed 69 90 88 \n",
"2 none 90 95 93 \n",
"3 none 47 57 44 \n",
"4 none 76 78 75 "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 1\n",
"data = pd.read_csv('exams.csv')\n",
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "d3QuVLdTOlma",
"outputId": "8be02567-aab0-4869-ec64-b4ff7621d071"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 1000 entries, 0 to 999\n",
"Data columns (total 8 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 gender 1000 non-null object\n",
" 1 race/ethnicity 1000 non-null object\n",
" 2 parental level of education 1000 non-null object\n",
" 3 lunch 1000 non-null object\n",
" 4 test preparation course 1000 non-null object\n",
" 5 math score 1000 non-null int64 \n",
" 6 reading score 1000 non-null int64 \n",
" 7 writing score 1000 non-null int64 \n",
"dtypes: int64(3), object(5)\n",
"memory usage: 62.6+ KB\n"
]
}
],
"source": [
"# 2\n",
"data.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "DLL5yr6yOlmb",
"outputId": "f08a0e3d-a37b-48e7-bea4-ee8571ebffe9"
},
"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>math score</th>\n",
" <th>reading score</th>\n",
" <th>writing score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>1000.00000</td>\n",
" <td>1000.000000</td>\n",
" <td>1000.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>66.08900</td>\n",
" <td>69.169000</td>\n",
" <td>68.054000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>15.16308</td>\n",
" <td>14.600192</td>\n",
" <td>15.195657</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>0.00000</td>\n",
" <td>17.000000</td>\n",
" <td>10.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>57.00000</td>\n",
" <td>59.000000</td>\n",
" <td>57.750000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>66.00000</td>\n",
" <td>70.000000</td>\n",
" <td>69.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>77.00000</td>\n",
" <td>79.000000</td>\n",
" <td>79.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>100.00000</td>\n",
" <td>100.000000</td>\n",
" <td>100.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" math score reading score writing score\n",
"count 1000.00000 1000.000000 1000.000000\n",
"mean 66.08900 69.169000 68.054000\n",
"std 15.16308 14.600192 15.195657\n",
"min 0.00000 17.000000 10.000000\n",
"25% 57.00000 59.000000 57.750000\n",
"50% 66.00000 70.000000 69.000000\n",
"75% 77.00000 79.000000 79.000000\n",
"max 100.00000 100.000000 100.000000"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 3\n",
"data.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ptOv6d0yOlmc",
"outputId": "68f6d45c-2523-43d1-e9e0-da78cc308fff"
},
"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>math score</th>\n",
" <th>reading score</th>\n",
" <th>writing score</th>\n",
" </tr>\n",
" <tr>\n",
" <th>race/ethnicity</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>group A</th>\n",
" <td>61.629213</td>\n",
" <td>64.674157</td>\n",
" <td>62.674157</td>\n",
" </tr>\n",
" <tr>\n",
" <th>group B</th>\n",
" <td>63.452632</td>\n",
" <td>67.352632</td>\n",
" <td>65.600000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>group C</th>\n",
" <td>64.463950</td>\n",
" <td>69.103448</td>\n",
" <td>67.827586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>group D</th>\n",
" <td>67.362595</td>\n",
" <td>70.030534</td>\n",
" <td>70.145038</td>\n",
" </tr>\n",
" <tr>\n",
" <th>group E</th>\n",
" <td>73.821429</td>\n",
" <td>73.028571</td>\n",
" <td>71.407143</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" math score reading score writing score\n",
"race/ethnicity \n",
"group A 61.629213 64.674157 62.674157\n",
"group B 63.452632 67.352632 65.600000\n",
"group C 64.463950 69.103448 67.827586\n",
"group D 67.362595 70.030534 70.145038\n",
"group E 73.821429 73.028571 71.407143"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 4\n",
"data.groupby('race/ethnicity').mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "9Rzy-LZDOlmd",
"outputId": "5e77ce81-6cf5-461b-d12c-707669183dd6"
},
"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>gender</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>995</th>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>female</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1000 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" gender\n",
"0 female\n",
"1 female\n",
"2 female\n",
"3 male\n",
"4 male\n",
".. ...\n",
"995 female\n",
"996 male\n",
"997 female\n",
"998 female\n",
"999 female\n",
"\n",
"[1000 rows x 1 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 5\n",
"data[['gender']]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "rtZX3vjkOlme",
"outputId": "4594f58b-deae-4353-c2d4-76eb180d1c7f"
},
"outputs": [
{
"data": {
"text/plain": [
"0 female\n",
"1 female\n",
"2 female\n",
"3 male\n",
"4 male\n",
" ... \n",
"995 female\n",
"996 male\n",
"997 female\n",
"998 female\n",
"999 female\n",
"Name: gender, Length: 1000, dtype: object"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 6\n",
"data['gender']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "5gaMm7FoOlme",
"outputId": "3dfd77d6-0f6a-4105-d3ea-36885dff08e2"
},
"outputs": [
{
"data": {
"text/plain": [
"0 female\n",
"1 female\n",
"2 female\n",
"3 male\n",
"4 male\n",
" ... \n",
"995 female\n",
"996 male\n",
"997 female\n",
"998 female\n",
"999 female\n",
"Name: gender, Length: 1000, dtype: object"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 7\n",
"data.gender"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "5Mi4RGEGOlmf",
"outputId": "b338b4ce-a31f-4086-cbaf-f8971280fe1f"
},
"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>gender</th>\n",
" <th>race/ethnicity</th>\n",
" <th>parental level of education</th>\n",
" <th>lunch</th>\n",
" <th>test preparation course</th>\n",
" <th>math score</th>\n",
" <th>reading score</th>\n",
" <th>writing score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>master's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>90</td>\n",
" <td>95</td>\n",
" <td>93</td>\n",
" </tr>\n",
" <tr>\n",
" <th>114</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>bachelor's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>99</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>165</th>\n",
" <td>female</td>\n",
" <td>group C</td>\n",
" <td>bachelor's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>96</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>179</th>\n",
" <td>female</td>\n",
" <td>group D</td>\n",
" <td>some high school</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>97</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>263</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>high school</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>99</td>\n",
" <td>93</td>\n",
" <td>90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>451</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>some college</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>100</td>\n",
" <td>92</td>\n",
" <td>97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>458</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>bachelor's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>474</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>90</td>\n",
" <td>90</td>\n",
" <td>91</td>\n",
" </tr>\n",
" <tr>\n",
" <th>501</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>94</td>\n",
" <td>87</td>\n",
" <td>92</td>\n",
" </tr>\n",
" <tr>\n",
" <th>503</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>95</td>\n",
" <td>89</td>\n",
" <td>92</td>\n",
" </tr>\n",
" <tr>\n",
" <th>521</th>\n",
" <td>female</td>\n",
" <td>group C</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>91</td>\n",
" <td>86</td>\n",
" <td>84</td>\n",
" </tr>\n",
" <tr>\n",
" <th>546</th>\n",
" <td>female</td>\n",
" <td>group A</td>\n",
" <td>some high school</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>92</td>\n",
" <td>100</td>\n",
" <td>97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>566</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>bachelor's degree</td>\n",
" <td>free/reduced</td>\n",
" <td>completed</td>\n",
" <td>92</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>594</th>\n",
" <td>female</td>\n",
" <td>group C</td>\n",
" <td>bachelor's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>92</td>\n",
" <td>100</td>\n",
" <td>99</td>\n",
" </tr>\n",
" <tr>\n",
" <th>685</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>master's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>94</td>\n",
" <td>99</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>712</th>\n",
" <td>female</td>\n",
" <td>group D</td>\n",
" <td>some college</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>98</td>\n",
" <td>100</td>\n",
" <td>99</td>\n",
" </tr>\n",
" <tr>\n",
" <th>717</th>\n",
" <td>female</td>\n",
" <td>group C</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>96</td>\n",
" <td>96</td>\n",
" <td>99</td>\n",
" </tr>\n",
" <tr>\n",
" <th>855</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>bachelor's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>97</td>\n",
" <td>97</td>\n",
" <td>96</td>\n",
" </tr>\n",
" <tr>\n",
" <th>886</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>93</td>\n",
" <td>100</td>\n",
" <td>95</td>\n",
" </tr>\n",
" <tr>\n",
" <th>903</th>\n",
" <td>female</td>\n",
" <td>group D</td>\n",
" <td>bachelor's degree</td>\n",
" <td>free/reduced</td>\n",
" <td>completed</td>\n",
" <td>93</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>957</th>\n",
" <td>female</td>\n",
" <td>group D</td>\n",
" <td>master's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>92</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>962</th>\n",
" <td>female</td>\n",
" <td>group E</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>979</th>\n",
" <td>female</td>\n",
" <td>group C</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>91</td>\n",
" <td>95</td>\n",
" <td>94</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" gender race/ethnicity parental level of education lunch \\\n",
"2 female group B master's degree standard \n",
"114 female group E bachelor's degree standard \n",
"165 female group C bachelor's degree standard \n",
"179 female group D some high school standard \n",
"263 female group E high school standard \n",
"451 female group E some college standard \n",
"458 female group E bachelor's degree standard \n",
"474 female group B associate's degree standard \n",
"501 female group B associate's degree standard \n",
"503 female group E associate's degree standard \n",
"521 female group C associate's degree standard \n",
"546 female group A some high school standard \n",
"566 female group E bachelor's degree free/reduced \n",
"594 female group C bachelor's degree standard \n",
"685 female group E master's degree standard \n",
"712 female group D some college standard \n",
"717 female group C associate's degree standard \n",
"855 female group B bachelor's degree standard \n",
"886 female group E associate's degree standard \n",
"903 female group D bachelor's degree free/reduced \n",
"957 female group D master's degree standard \n",
"962 female group E associate's degree standard \n",
"979 female group C associate's degree standard \n",
"\n",
" test preparation course math score reading score writing score \n",
"2 none 90 95 93 \n",
"114 completed 99 100 100 \n",
"165 completed 96 100 100 \n",
"179 completed 97 100 100 \n",
"263 none 99 93 90 \n",
"451 none 100 92 97 \n",
"458 none 100 100 100 \n",
"474 completed 90 90 91 \n",
"501 completed 94 87 92 \n",
"503 completed 95 89 92 \n",
"521 none 91 86 84 \n",
"546 completed 92 100 97 \n",
"566 completed 92 100 100 \n",
"594 completed 92 100 99 \n",
"685 completed 94 99 100 \n",
"712 none 98 100 99 \n",
"717 completed 96 96 99 \n",
"855 none 97 97 96 \n",
"886 completed 93 100 95 \n",
"903 completed 93 100 100 \n",
"957 none 92 100 100 \n",
"962 none 100 100 100 \n",
"979 none 91 95 94 "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 8\n",
"data.query('gender == \"female\" and `math score` >= 90')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qKAOs0liOlmg"
},
"source": [
"## Questions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "5D7AGOupOlmh",
"outputId": "09c8448f-abce-45b4-f4c4-14e518072dbd"
},
"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>math score</th>\n",
" <th>reading score</th>\n",
" <th>writing score</th>\n",
" </tr>\n",
" <tr>\n",
" <th>test preparation course</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>completed</th>\n",
" <td>69.695531</td>\n",
" <td>73.893855</td>\n",
" <td>74.418994</td>\n",
" </tr>\n",
" <tr>\n",
" <th>none</th>\n",
" <td>64.077882</td>\n",
" <td>66.534268</td>\n",
" <td>64.504673</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" math score reading score writing score\n",
"test preparation course \n",
"completed 69.695531 73.893855 74.418994\n",
"none 64.077882 66.534268 64.504673"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 1\n",
"data.groupby('test preparation course').mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "swpev9BaOlmh",
"outputId": "481f250a-a781-4c32-b3a9-5e59c08735b8"
},
"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>math score</th>\n",
" </tr>\n",
" <tr>\n",
" <th>gender</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>female</th>\n",
" <td>63.633205</td>\n",
" </tr>\n",
" <tr>\n",
" <th>male</th>\n",
" <td>68.728216</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" math score\n",
"gender \n",
"female 63.633205\n",
"male 68.728216"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 2\n",
"data.groupby('gender')[['math score']].mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "4dElSz5POlmi",
"outputId": "c6dc8c47-7268-4ca1-c32c-67f36cfb86ec"
},
"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>total score</th>\n",
" </tr>\n",
" <tr>\n",
" <th>gender</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>female</th>\n",
" <td>208.708494</td>\n",
" </tr>\n",
" <tr>\n",
" <th>male</th>\n",
" <td>197.512448</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" total score\n",
"gender \n",
"female 208.708494\n",
"male 197.512448"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 3\n",
"data['total score'] = data['math score'] + data['reading score'] + data['writing score']\n",
"data.groupby('gender')[['total score']].mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "xSRmlTJkOlmi",
"outputId": "02c9a3f9-37f7-43b5-e3c3-1663703855b2"
},
"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>math score</th>\n",
" <th>reading score</th>\n",
" <th>writing score</th>\n",
" <th>total score</th>\n",
" </tr>\n",
" <tr>\n",
" <th>parental level of education</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>master's degree</th>\n",
" <td>69.745763</td>\n",
" <td>75.372881</td>\n",
" <td>75.677966</td>\n",
" <td>220.796610</td>\n",
" </tr>\n",
" <tr>\n",
" <th>bachelor's degree</th>\n",
" <td>69.389831</td>\n",
" <td>73.000000</td>\n",
" <td>73.381356</td>\n",
" <td>215.771186</td>\n",
" </tr>\n",
" <tr>\n",
" <th>associate's degree</th>\n",
" <td>67.882883</td>\n",
" <td>70.927928</td>\n",
" <td>69.896396</td>\n",
" <td>208.707207</td>\n",
" </tr>\n",
" <tr>\n",
" <th>some college</th>\n",
" <td>67.128319</td>\n",
" <td>69.460177</td>\n",
" <td>68.840708</td>\n",
" <td>205.429204</td>\n",
" </tr>\n",
" <tr>\n",
" <th>some high school</th>\n",
" <td>63.497207</td>\n",
" <td>66.938547</td>\n",
" <td>64.888268</td>\n",
" <td>195.324022</td>\n",
" </tr>\n",
" <tr>\n",
" <th>high school</th>\n",
" <td>62.137755</td>\n",
" <td>64.704082</td>\n",
" <td>62.448980</td>\n",
" <td>189.290816</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" math score reading score writing score \\\n",
"parental level of education \n",
"master's degree 69.745763 75.372881 75.677966 \n",
"bachelor's degree 69.389831 73.000000 73.381356 \n",
"associate's degree 67.882883 70.927928 69.896396 \n",
"some college 67.128319 69.460177 68.840708 \n",
"some high school 63.497207 66.938547 64.888268 \n",
"high school 62.137755 64.704082 62.448980 \n",
"\n",
" total score \n",
"parental level of education \n",
"master's degree 220.796610 \n",
"bachelor's degree 215.771186 \n",
"associate's degree 208.707207 \n",
"some college 205.429204 \n",
"some high school 195.324022 \n",
"high school 189.290816 "
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 4\n",
"data.groupby('parental level of education').mean().sort_values(by=['math score','reading score','writing score'], ascending=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "0I8YjfMIOlmi"
},
"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": "3.8.8"
},
"colab": {
"provenance": [],
"include_colab_link": true
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment