Skip to content

Instantly share code, notes, and snippets.

@fenago

fenago/proj_7-2_avocado.ipynb

Created October 23, 2024 07:50
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save fenago/b30863df42d2e1e324cbd551a8533958 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save fenago/b30863df42d2e1e324cbd551a8533958 to your computer and use it in GitHub Desktop.
Download ZIP
proj_7-2_avocado.ipynb
Display the source blob
Display the rendered blob
Raw
proj_7-2_avocado.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/fenago/b30863df42d2e1e324cbd551a8533958/proj_7-2_avocado.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rs9LbMvBW1By"
},
"source": [
"# Project 7-2: Prepare the avocado data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "2Ruwg96RW1B3"
},
"outputs": [],
"source": [
"# https://www.kaggle.com/neuromusic/avocado-prices\n",
"import pandas as pd"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "SfbvJGOrW1B6"
},
"source": [
"## Tasks"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "6Ei9njN7W1B7",
"outputId": "b1e44720-e814-41c2-e77f-1bc880a9ec47"
},
"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>Unnamed: 0</th>\n",
" <th>Date</th>\n",
" <th>AveragePrice</th>\n",
" <th>Total Volume</th>\n",
" <th>4046</th>\n",
" <th>4225</th>\n",
" <th>4770</th>\n",
" <th>Total Bags</th>\n",
" <th>Small Bags</th>\n",
" <th>Large Bags</th>\n",
" <th>XLarge Bags</th>\n",
" <th>type</th>\n",
" <th>year</th>\n",
" <th>region</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>2015-12-27</td>\n",
" <td>1.33</td>\n",
" <td>64236.62</td>\n",
" <td>1036.74</td>\n",
" <td>54454.85</td>\n",
" <td>48.16</td>\n",
" <td>8696.87</td>\n",
" <td>8603.62</td>\n",
" <td>93.25</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>2015-12-20</td>\n",
" <td>1.35</td>\n",
" <td>54876.98</td>\n",
" <td>674.28</td>\n",
" <td>44638.81</td>\n",
" <td>58.33</td>\n",
" <td>9505.56</td>\n",
" <td>9408.07</td>\n",
" <td>97.49</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>2015-12-13</td>\n",
" <td>0.93</td>\n",
" <td>118220.22</td>\n",
" <td>794.70</td>\n",
" <td>109149.67</td>\n",
" <td>130.50</td>\n",
" <td>8145.35</td>\n",
" <td>8042.21</td>\n",
" <td>103.14</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>2015-12-06</td>\n",
" <td>1.08</td>\n",
" <td>78992.15</td>\n",
" <td>1132.00</td>\n",
" <td>71976.41</td>\n",
" <td>72.58</td>\n",
" <td>5811.16</td>\n",
" <td>5677.40</td>\n",
" <td>133.76</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>2015-11-29</td>\n",
" <td>1.28</td>\n",
" <td>51039.60</td>\n",
" <td>941.48</td>\n",
" <td>43838.39</td>\n",
" <td>75.78</td>\n",
" <td>6183.95</td>\n",
" <td>5986.26</td>\n",
" <td>197.69</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 Date AveragePrice Total Volume 4046 4225 \\\n",
"0 0 2015-12-27 1.33 64236.62 1036.74 54454.85 \n",
"1 1 2015-12-20 1.35 54876.98 674.28 44638.81 \n",
"2 2 2015-12-13 0.93 118220.22 794.70 109149.67 \n",
"3 3 2015-12-06 1.08 78992.15 1132.00 71976.41 \n",
"4 4 2015-11-29 1.28 51039.60 941.48 43838.39 \n",
"\n",
" 4770 Total Bags Small Bags Large Bags XLarge Bags type \\\n",
"0 48.16 8696.87 8603.62 93.25 0.0 conventional \n",
"1 58.33 9505.56 9408.07 97.49 0.0 conventional \n",
"2 130.50 8145.35 8042.21 103.14 0.0 conventional \n",
"3 72.58 5811.16 5677.40 133.76 0.0 conventional \n",
"4 75.78 6183.95 5986.26 197.69 0.0 conventional \n",
"\n",
" year region \n",
"0 2015 Albany \n",
"1 2015 Albany \n",
"2 2015 Albany \n",
"3 2015 Albany \n",
"4 2015 Albany "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 1\n",
"data = pd.read_csv('avocado.csv')\n",
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Xhujyx5-W1B_",
"outputId": "b3ae2830-ac7b-4b97-8775-3196fec3dae2"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 18249 entries, 0 to 18248\n",
"Data columns (total 14 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Unnamed:0 18249 non-null int64 \n",
" 1 Date 18249 non-null object \n",
" 2 AveragePrice 18249 non-null float64\n",
" 3 TotalVolume 18249 non-null float64\n",
" 4 4046 18249 non-null float64\n",
" 5 4225 18249 non-null float64\n",
" 6 4770 18249 non-null float64\n",
" 7 TotalBags 18249 non-null float64\n",
" 8 SmallBags 18249 non-null float64\n",
" 9 LargeBags 18249 non-null float64\n",
" 10 XlargeBags 18249 non-null float64\n",
" 11 Type 18249 non-null object \n",
" 12 Year 18249 non-null int64 \n",
" 13 Region 18249 non-null object \n",
"dtypes: float64(9), int64(2), object(3)\n",
"memory usage: 1.9+ MB\n"
]
}
],
"source": [
"# 2\n",
"\n",
"# convert the columns to a list\n",
"allCols = data.columns.tolist()\n",
"\n",
"# create a new list with the formatted column names\n",
"newCols = []\n",
"for col in allCols:\n",
" c = ''.join(col.title().split(' '))\n",
" newCols.append(c)\n",
"\n",
"# assign the list of columns to the columns attribute\n",
"data.columns = newCols\n",
"\n",
"# rename the Averageprice column to AveragePrice\n",
"data.rename(columns={'Averageprice':'AveragePrice'}, inplace=True)\n",
"\n",
"# check that the columns have been renamed\n",
"data.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Qt4NmCarW1CA"
},
"outputs": [],
"source": [
"# 3\n",
"data['XLargePercent'] = data['XlargeBags'] / data['TotalBags']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "VIwZ5L2EW1CA"
},
"outputs": [],
"source": [
"# 4\n",
"data['LargePercent'] = data['LargeBags'] / data['TotalBags']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Km7xcq0vW1CB"
},
"outputs": [],
"source": [
"# 5\n",
"data['SmallPercent'] = data['SmallBags'] / data['TotalBags']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "mjXEHwFMW1CB",
"outputId": "b3985b4c-479a-4f8c-9e1c-f8b300259388"
},
"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>Unnamed:0</th>\n",
" <th>Date</th>\n",
" <th>AveragePrice</th>\n",
" <th>TotalVolume</th>\n",
" <th>4046</th>\n",
" <th>4225</th>\n",
" <th>4770</th>\n",
" <th>TotalBags</th>\n",
" <th>SmallBags</th>\n",
" <th>LargeBags</th>\n",
" <th>XlargeBags</th>\n",
" <th>Type</th>\n",
" <th>Year</th>\n",
" <th>Region</th>\n",
" <th>XLargePercent</th>\n",
" <th>LargePercent</th>\n",
" <th>SmallPercent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>2015-12-27</td>\n",
" <td>1.33</td>\n",
" <td>64236.62</td>\n",
" <td>1036.74</td>\n",
" <td>54454.85</td>\n",
" <td>48.16</td>\n",
" <td>8696.87</td>\n",
" <td>8603.62</td>\n",
" <td>93.25</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" <td>0.0</td>\n",
" <td>0.010722</td>\n",
" <td>0.989278</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>2015-12-20</td>\n",
" <td>1.35</td>\n",
" <td>54876.98</td>\n",
" <td>674.28</td>\n",
" <td>44638.81</td>\n",
" <td>58.33</td>\n",
" <td>9505.56</td>\n",
" <td>9408.07</td>\n",
" <td>97.49</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" <td>0.0</td>\n",
" <td>0.010256</td>\n",
" <td>0.989744</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>2015-12-13</td>\n",
" <td>0.93</td>\n",
" <td>118220.22</td>\n",
" <td>794.70</td>\n",
" <td>109149.67</td>\n",
" <td>130.50</td>\n",
" <td>8145.35</td>\n",
" <td>8042.21</td>\n",
" <td>103.14</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" <td>0.0</td>\n",
" <td>0.012662</td>\n",
" <td>0.987338</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>2015-12-06</td>\n",
" <td>1.08</td>\n",
" <td>78992.15</td>\n",
" <td>1132.00</td>\n",
" <td>71976.41</td>\n",
" <td>72.58</td>\n",
" <td>5811.16</td>\n",
" <td>5677.40</td>\n",
" <td>133.76</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" <td>0.0</td>\n",
" <td>0.023018</td>\n",
" <td>0.976982</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>2015-11-29</td>\n",
" <td>1.28</td>\n",
" <td>51039.60</td>\n",
" <td>941.48</td>\n",
" <td>43838.39</td>\n",
" <td>75.78</td>\n",
" <td>6183.95</td>\n",
" <td>5986.26</td>\n",
" <td>197.69</td>\n",
" <td>0.0</td>\n",
" <td>conventional</td>\n",
" <td>2015</td>\n",
" <td>Albany</td>\n",
" <td>0.0</td>\n",
" <td>0.031968</td>\n",
" <td>0.968032</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed:0 Date AveragePrice TotalVolume 4046 4225 \\\n",
"0 0 2015-12-27 1.33 64236.62 1036.74 54454.85 \n",
"1 1 2015-12-20 1.35 54876.98 674.28 44638.81 \n",
"2 2 2015-12-13 0.93 118220.22 794.70 109149.67 \n",
"3 3 2015-12-06 1.08 78992.15 1132.00 71976.41 \n",
"4 4 2015-11-29 1.28 51039.60 941.48 43838.39 \n",
"\n",
" 4770 TotalBags SmallBags LargeBags XlargeBags Type Year \\\n",
"0 48.16 8696.87 8603.62 93.25 0.0 conventional 2015 \n",
"1 58.33 9505.56 9408.07 97.49 0.0 conventional 2015 \n",
"2 130.50 8145.35 8042.21 103.14 0.0 conventional 2015 \n",
"3 72.58 5811.16 5677.40 133.76 0.0 conventional 2015 \n",
"4 75.78 6183.95 5986.26 197.69 0.0 conventional 2015 \n",
"\n",
" Region XLargePercent LargePercent SmallPercent \n",
"0 Albany 0.0 0.010722 0.989278 \n",
"1 Albany 0.0 0.010256 0.989744 \n",
"2 Albany 0.0 0.012662 0.987338 \n",
"3 Albany 0.0 0.023018 0.976982 \n",
"4 Albany 0.0 0.031968 0.968032 "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 6\n",
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "88GNw8efW1CC"
},
"outputs": [],
"source": [
"# 7\n",
"dataReduced = data[['Region','Type','Year','TotalBags']]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ML3vkyCAW1CD",
"outputId": "73cc2811-8ce8-4f4f-e44c-8900cb749508"
},
"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 tr th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe thead tr:last-of-type th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th></th>\n",
" <th colspan=\"2\" halign=\"left\">TotalBags</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>Type</th>\n",
" <th>conventional</th>\n",
" <th>organic</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Region</th>\n",
" <th>Year</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">Albany</th>\n",
" <th>2015</th>\n",
" <td>662366.17</td>\n",
" <td>57289.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2016</th>\n",
" <td>759091.14</td>\n",
" <td>79208.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017</th>\n",
" <td>699561.17</td>\n",
" <td>135944.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2018</th>\n",
" <td>245240.75</td>\n",
" <td>41552.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Atlanta</th>\n",
" <th>2015</th>\n",
" <td>2935925.63</td>\n",
" <td>61065.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>West</th>\n",
" <th>2018</th>\n",
" <td>35978608.70</td>\n",
" <td>2074684.34</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">WestTexNewMexico</th>\n",
" <th>2015</th>\n",
" <td>5399316.40</td>\n",
" <td>128763.94</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2016</th>\n",
" <td>10870856.07</td>\n",
" <td>403881.08</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017</th>\n",
" <td>14195031.44</td>\n",
" <td>602152.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2018</th>\n",
" <td>3547372.46</td>\n",
" <td>149141.90</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>216 rows × 2 columns</p>\n",
"</div>"
],
"text/plain": [
" TotalBags \n",
"Type conventional organic\n",
"Region Year \n",
"Albany 2015 662366.17 57289.43\n",
" 2016 759091.14 79208.77\n",
" 2017 699561.17 135944.43\n",
" 2018 245240.75 41552.75\n",
"Atlanta 2015 2935925.63 61065.24\n",
"... ... ...\n",
"West 2018 35978608.70 2074684.34\n",
"WestTexNewMexico 2015 5399316.40 128763.94\n",
" 2016 10870856.07 403881.08\n",
" 2017 14195031.44 602152.24\n",
" 2018 3547372.46 149141.90\n",
"\n",
"[216 rows x 2 columns]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 8\n",
"dataGrouped = dataReduced.groupby(['Region','Type','Year']).sum().unstack('Type')\n",
"dataGrouped"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "D_gFbY_4W1CD"
},
"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