BbsonLin
/
analytics-data
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
master
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'master'
${ noResults }
analytics-data/practice.ipynb

542 lines
16 KiB
Plaintext
Raw Permalink Blame History Unescape Escape

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"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>國家/地區</th>\n",
" <th>使用者</th>\n",
" <th>新使用者</th>\n",
" <th>工作階段</th>\n",
" <th>跳出率</th>\n",
" <th>單次工作階段頁數</th>\n",
" <th>平均工作階段時間長度</th>\n",
" <th>目標轉換率</th>\n",
" <th>目標達成</th>\n",
" <th>目標價值</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Taiwan</td>\n",
" <td>322</td>\n",
" <td>243</td>\n",
" <td>388</td>\n",
" <td>0.030928</td>\n",
" <td>6.510309</td>\n",
" <td>204.479381</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>United States</td>\n",
" <td>172</td>\n",
" <td>157</td>\n",
" <td>194</td>\n",
" <td>0.118557</td>\n",
" <td>3.500000</td>\n",
" <td>77.798969</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>China</td>\n",
" <td>141</td>\n",
" <td>113</td>\n",
" <td>202</td>\n",
" <td>0.064356</td>\n",
" <td>6.391089</td>\n",
" <td>226.856436</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>India</td>\n",
" <td>112</td>\n",
" <td>84</td>\n",
" <td>159</td>\n",
" <td>0.050314</td>\n",
" <td>6.188679</td>\n",
" <td>174.012579</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Germany</td>\n",
" <td>67</td>\n",
" <td>53</td>\n",
" <td>94</td>\n",
" <td>0.010638</td>\n",
" <td>7.510638</td>\n",
" <td>195.957447</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 國家/地區 使用者 新使用者 工作階段 跳出率 單次工作階段頁數 平均工作階段時間長度 目標轉換率 \\\n",
"0 Taiwan 322 243 388 0.030928 6.510309 204.479381 0 \n",
"1 United States 172 157 194 0.118557 3.500000 77.798969 0 \n",
"2 China 141 113 202 0.064356 6.391089 226.856436 0 \n",
"3 India 112 84 159 0.050314 6.188679 174.012579 0 \n",
"4 Germany 67 53 94 0.010638 7.510638 195.957447 0 \n",
"\n",
" 目標達成 目標價值 \n",
"0 0 0 \n",
"1 0 0 \n",
"2 0 0 \n",
"3 0 0 \n",
"4 0 0 "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"regions = pd.read_excel('./data/Analytics 所有網站資料 地區 20190217-20190223.xlsx',\n",
" sheet_name=\"資料集1\")\n",
"regions.head()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"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>國家/地區</th>\n",
" <th>Taiwan</th>\n",
" <th>United States</th>\n",
" <th>China</th>\n",
" <th>India</th>\n",
" <th>Germany</th>\n",
" <th>Italy</th>\n",
" <th>France</th>\n",
" <th>United Kingdom</th>\n",
" <th>South Korea</th>\n",
" <th>Russia</th>\n",
" <th>...</th>\n",
" <th>Kyrgyzstan</th>\n",
" <th>Kuwait</th>\n",
" <th>Kazakhstan</th>\n",
" <th>Mexico</th>\n",
" <th>Namibia</th>\n",
" <th>Puerto Rico</th>\n",
" <th>Slovenia</th>\n",
" <th>Samoa</th>\n",
" <th>South Africa</th>\n",
" <th>nan</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>使用者</th>\n",
" <td>322</td>\n",
" <td>172</td>\n",
" <td>141</td>\n",
" <td>112</td>\n",
" <td>67</td>\n",
" <td>56</td>\n",
" <td>54</td>\n",
" <td>49</td>\n",
" <td>47</td>\n",
" <td>44</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1405</td>\n",
" </tr>\n",
" <tr>\n",
" <th>新使用者</th>\n",
" <td>243</td>\n",
" <td>157</td>\n",
" <td>113</td>\n",
" <td>84</td>\n",
" <td>53</td>\n",
" <td>41</td>\n",
" <td>46</td>\n",
" <td>30</td>\n",
" <td>34</td>\n",
" <td>34</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1099</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2 rows × 67 columns</p>\n",
"</div>"
],
"text/plain": [
"國家/地區 Taiwan United States China India Germany Italy France \\\n",
"使用者 322 172 141 112 67 56 54 \n",
"新使用者 243 157 113 84 53 41 46 \n",
"\n",
"國家/地區 United Kingdom South Korea Russia ... Kyrgyzstan Kuwait \\\n",
"使用者 49 47 44 ... 1 1 \n",
"新使用者 30 34 34 ... 1 1 \n",
"\n",
"國家/地區 Kazakhstan Mexico Namibia Puerto Rico Slovenia Samoa \\\n",
"使用者 1 1 1 1 1 1 \n",
"新使用者 0 1 1 1 1 1 \n",
"\n",
"國家/地區 South Africa NaN \n",
"使用者 1 1405 \n",
"新使用者 0 1099 \n",
"\n",
"[2 rows x 67 columns]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"regions.set_index('國家/地區', inplace=True)\n",
"regions.loc[:, '使用者':'新使用者'].T"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"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>社交網路</th>\n",
" <th>國家/地區</th>\n",
" <th>使用者</th>\n",
" <th>新使用者</th>\n",
" <th>工作階段</th>\n",
" <th>跳出率</th>\n",
" <th>單次工作階段頁數</th>\n",
" <th>平均工作階段時間長度</th>\n",
" <th>目標轉換率</th>\n",
" <th>目標達成</th>\n",
" <th>目標價值</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Facebook</td>\n",
" <td>Taiwan</td>\n",
" <td>20</td>\n",
" <td>13</td>\n",
" <td>22</td>\n",
" <td>0.181818</td>\n",
" <td>2.818182</td>\n",
" <td>9.454545</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Facebook</td>\n",
" <td>United States</td>\n",
" <td>14</td>\n",
" <td>13</td>\n",
" <td>14</td>\n",
" <td>0.071429</td>\n",
" <td>1.928571</td>\n",
" <td>1.142857</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Naver</td>\n",
" <td>South Korea</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>11</td>\n",
" <td>0.000000</td>\n",
" <td>5.545455</td>\n",
" <td>202.272727</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>LinkedIn</td>\n",
" <td>United States</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0.000000</td>\n",
" <td>4.000000</td>\n",
" <td>20.000000</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Twitter</td>\n",
" <td>Italy</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0.000000</td>\n",
" <td>4.500000</td>\n",
" <td>892.500000</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 社交網路 國家/地區 使用者 新使用者 工作階段 跳出率 單次工作階段頁數 平均工作階段時間長度 \\\n",
"0 Facebook Taiwan 20 13 22 0.181818 2.818182 9.454545 \n",
"1 Facebook United States 14 13 14 0.071429 1.928571 1.142857 \n",
"2 Naver South Korea 6 5 11 0.000000 5.545455 202.272727 \n",
"3 LinkedIn United States 2 0 2 0.000000 4.000000 20.000000 \n",
"4 Twitter Italy 2 2 2 0.000000 4.500000 892.500000 \n",
"\n",
" 目標轉換率 目標達成 目標價值 \n",
"0 0 0 0 \n",
"1 0 0 0 \n",
"2 0 0 0 \n",
"3 0 0 0 \n",
"4 0 0 0 "
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"social = pd.read_excel('./data/Analytics 所有網站資料 管道 20190217-20190223 (1).xlsx',\n",
" sheet_name=\"資料集1\")\n",
"social.head()"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"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>使用者</th>\n",
" <th>新使用者</th>\n",
" </tr>\n",
" <tr>\n",
" <th>社交網路</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Facebook</th>\n",
" <td>35</td>\n",
" <td>27</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Instagram</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>LinkedIn</th>\n",
" <td>6</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Naver</th>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Twitter</th>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 使用者 新使用者\n",
"社交網路 \n",
"Facebook 35 27\n",
"Instagram 1 1\n",
"LinkedIn 6 2\n",
"Naver 6 5\n",
"Twitter 3 3"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"social.groupby('社交網路').sum().loc[:, '使用者':'新使用者']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"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": "3.6.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue View Git Blame Copy Permalink