Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
F
ffm-baseline
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
ML
ffm-baseline
Commits
85228951
Commit
85228951
authored
Aug 06, 2018
by
高雅喆
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
delete test
parent
8b11ce8d
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
0 additions
and
1884 deletions
+0
-1884
Untitled-checkpoint.ipynb
.ipynb_checkpoints/Untitled-checkpoint.ipynb
+0
-942
Untitled.ipynb
Untitled.ipynb
+0
-942
No files found.
.ipynb_checkpoints/Untitled-checkpoint.ipynb
deleted
100644 → 0
View file @
8b11ce8d
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"FfmEncoder.py small_click.csv test_last.ffm train_last.ffm.bin\r\n",
"Untitled.ipynb test_clk.ffm test_last.ffm.bin train_shuf.ffm\r\n",
"model.out test_clk.ffm.bin train_all.csv\r\n",
"output.txt test_imp.ffm train_all.ffm\r\n",
"run_demo_ctr.py test_imp.ffm.bin train_last.ffm\r\n"
]
}
],
"source": [
"ls"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.read_table(\"output.txt\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0.389993</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>9998.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>0.239161</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>0.258047</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>0.018704</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>0.064364</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>0.113151</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>0.279245</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>0.923141</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0.389993\n",
"count 9998.000000\n",
"mean 0.239161\n",
"std 0.258047\n",
"min 0.018704\n",
"25% 0.064364\n",
"50% 0.113151\n",
"75% 0.279245\n",
"max 0.923141"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(9999, 36)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\"small_click.csv\")\n",
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['article_type', 'cid', 'cid_id', 'cid_type', 'city_id',\n",
" 'click_count_choice', 'content_level', 'created_time', 'device_id',\n",
" 'device_type', 'device_view', 'diary_doctor_id', 'diary_new_favor',\n",
" 'diary_new_replies', 'diary_new_topic_replies', 'diary_new_topic_votes',\n",
" 'diary_new_topics', 'diary_service_id', 'diary_updated_time',\n",
" 'is_recommend', 'live_fake_max_num', 'live_is_finish',\n",
" 'live_max_view_num', 'live_replay_danmu', 'live_topic_id', 'new_votes',\n",
" 'page_view', 'question_answer_reply_num', 'reply_num', 'reply_vote_num',\n",
" 'show_count', 'show_count_choice', 'stat_date', 'time', 'user_view',\n",
" 'label'],\n",
" dtype='object')"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>cid</th>\n",
" </tr>\n",
" <tr>\n",
" <th>device_id</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0027137D-E16E-4BB1-9FC6-2EDA44FF1F5C</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0073F6BD-F93B-46D6-AE4F-46F70B5A7665</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0074C249-33DA-457E-8960-3B98DC8887C6</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008796749543200</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008796752520863</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008796762134609</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008AEF54-E367-475D-9614-27830B1AB6D1</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>00981796-12AE-4BDE-853C-A39037A5F8CE</th>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>00BAD771-8FDA-4739-AE10-78A708C97E8A</th>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>00CA20EB-2719-4518-85CC-60E765AC526F</th>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01126351-2DB2-4F39-B310-71783A03EE1C</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01188F61-0B48-41C7-A45A-7581A9D6EE48</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>013738A2-5886-48B5-A0C4-BF849B411CAC</th>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>014512241593985</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0155A2C3-FCBD-4248-8761-2F8D0AFEA49C</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>015C9051-1B61-4E10-AA29-32D989BBFE88</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01993D28-5D0A-4C8B-87B5-02211AA4E2C1</th>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01B86BB8-1A0C-40D3-9103-365A3A3498D6</th>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01CAA461-91AD-417E-9D75-AF8854F63A98</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01E35E1F-CAAF-42A0-A858-B545BD1C4455</th>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0241469B-967E-4445-AC8B-A9218771640A</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02754D73-5343-40B9-9DFF-43B04AC18A9F</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02B1800B-E29D-4899-95B6-A83CD8AD0954</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02C3201E-7A3C-4A94-972E-846036ECA970</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02C505F6-5186-4489-B478-823330FD4FA5</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02C744A4-90B9-43E4-ABA8-46560B2715AC</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02CB8A9D-CE29-403F-A87F-8C0245BCC804</th>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>030C3E1A-155C-47C4-8BE8-6BC20DCA3FD1</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>031FCF2A-8F5E-4312-BF48-E9F8F4710BD6</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>033B1FFB-31BA-4179-AC33-1369F1B21748</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e3b37c0f2ec18806</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e6a79883ab24c033</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e72d5572556a768a</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e7e288fc31427833</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e87d7b652273fb84</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e96b1117a08027c1</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_eb04dfe8020c4abf</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ec0d18f354bd4650</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ed37d88b405eba00</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_edd61267a99e4981</th>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_eddfd121ccfc308c</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ee4b1688ecb46676</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ee97be7ea5ef3417</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_efbfdb353bc23505</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f0f2132ee59a7fa4</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f1faded03ceab141</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f38ab0dba9bf1dd5</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f3e1cbf7fbd759f2</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f40916a405dc7ac5</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f515a007af34d7a</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f67e62bd514cfe32</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f6e89217fb8d4c86</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f7c24eb6908abdda</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f8554903cd899b8f</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f91cecf0d12a1cdc</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fc3410e808b9c8b6</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fc508414e32d3989</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fd724c132e4fb908</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fe5165a27249fd08</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_feba9a7d18f1054a</th>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>4318 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" cid\n",
"device_id \n",
"0027137D-E16E-4BB1-9FC6-2EDA44FF1F5C 1\n",
"0073F6BD-F93B-46D6-AE4F-46F70B5A7665 1\n",
"0074C249-33DA-457E-8960-3B98DC8887C6 1\n",
"008796749543200 1\n",
"008796752520863 1\n",
"008796762134609 1\n",
"008AEF54-E367-475D-9614-27830B1AB6D1 1\n",
"00981796-12AE-4BDE-853C-A39037A5F8CE 3\n",
"00BAD771-8FDA-4739-AE10-78A708C97E8A 9\n",
"00CA20EB-2719-4518-85CC-60E765AC526F 23\n",
"01126351-2DB2-4F39-B310-71783A03EE1C 4\n",
"01188F61-0B48-41C7-A45A-7581A9D6EE48 4\n",
"013738A2-5886-48B5-A0C4-BF849B411CAC 9\n",
"014512241593985 1\n",
"0155A2C3-FCBD-4248-8761-2F8D0AFEA49C 1\n",
"015C9051-1B61-4E10-AA29-32D989BBFE88 1\n",
"01993D28-5D0A-4C8B-87B5-02211AA4E2C1 3\n",
"01B86BB8-1A0C-40D3-9103-365A3A3498D6 5\n",
"01CAA461-91AD-417E-9D75-AF8854F63A98 1\n",
"01E35E1F-CAAF-42A0-A858-B545BD1C4455 3\n",
"0241469B-967E-4445-AC8B-A9218771640A 2\n",
"02754D73-5343-40B9-9DFF-43B04AC18A9F 1\n",
"02B1800B-E29D-4899-95B6-A83CD8AD0954 1\n",
"02C3201E-7A3C-4A94-972E-846036ECA970 1\n",
"02C505F6-5186-4489-B478-823330FD4FA5 1\n",
"02C744A4-90B9-43E4-ABA8-46560B2715AC 1\n",
"02CB8A9D-CE29-403F-A87F-8C0245BCC804 7\n",
"030C3E1A-155C-47C4-8BE8-6BC20DCA3FD1 2\n",
"031FCF2A-8F5E-4312-BF48-E9F8F4710BD6 2\n",
"033B1FFB-31BA-4179-AC33-1369F1B21748 1\n",
"... ...\n",
"androidid_e3b37c0f2ec18806 1\n",
"androidid_e6a79883ab24c033 1\n",
"androidid_e72d5572556a768a 1\n",
"androidid_e7e288fc31427833 2\n",
"androidid_e87d7b652273fb84 1\n",
"androidid_e96b1117a08027c1 1\n",
"androidid_eb04dfe8020c4abf 1\n",
"androidid_ec0d18f354bd4650 1\n",
"androidid_ed37d88b405eba00 1\n",
"androidid_edd61267a99e4981 5\n",
"androidid_eddfd121ccfc308c 1\n",
"androidid_ee4b1688ecb46676 2\n",
"androidid_ee97be7ea5ef3417 1\n",
"androidid_efbfdb353bc23505 1\n",
"androidid_f0f2132ee59a7fa4 1\n",
"androidid_f1faded03ceab141 4\n",
"androidid_f38ab0dba9bf1dd5 1\n",
"androidid_f3e1cbf7fbd759f2 2\n",
"androidid_f40916a405dc7ac5 1\n",
"androidid_f515a007af34d7a 2\n",
"androidid_f67e62bd514cfe32 1\n",
"androidid_f6e89217fb8d4c86 1\n",
"androidid_f7c24eb6908abdda 1\n",
"androidid_f8554903cd899b8f 2\n",
"androidid_f91cecf0d12a1cdc 1\n",
"androidid_fc3410e808b9c8b6 1\n",
"androidid_fc508414e32d3989 2\n",
"androidid_fd724c132e4fb908 1\n",
"androidid_fe5165a27249fd08 1\n",
"androidid_feba9a7d18f1054a 1\n",
"\n",
"[4318 rows x 1 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2 = df[[\"device_id\",\"cid\"]].groupby(\"device_id\").count()\n",
"df2"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x10b49cb38>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"df2.boxplot()\n",
"plt.ylabel(\"ARI\")\n",
"plt.xlabel(\"Dissimilarity Measures\")#我们设置横纵坐标的标题。\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data_a={'state':[1,1,2],'pop':['a','b','c']}\n",
"data_b={'state':[1,2,3],'pop':['b','c','d']}\n",
"a=pd.DataFrame(data_a)\n",
"b=pd.DataFrame(data_b) "
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 a 1\n",
"1 b 1\n",
"2 c 2"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"b"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"a = a.append(b);a = a.append(b)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 a 1\n",
"1 b 1\n",
"2 c 2\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"result = a.drop_duplicates(subset=['pop','state'],keep=False)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 a 1"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"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": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Untitled.ipynb
deleted
100644 → 0
View file @
8b11ce8d
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"FfmEncoder.py small_click.csv test_last.ffm train_last.ffm.bin\r\n",
"Untitled.ipynb test_clk.ffm test_last.ffm.bin train_shuf.ffm\r\n",
"model.out test_clk.ffm.bin train_all.csv\r\n",
"output.txt test_imp.ffm train_all.ffm\r\n",
"run_demo_ctr.py test_imp.ffm.bin train_last.ffm\r\n"
]
}
],
"source": [
"ls"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.read_table(\"output.txt\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0.389993</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>9998.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>0.239161</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>0.258047</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>0.018704</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>0.064364</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>0.113151</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>0.279245</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>0.923141</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0.389993\n",
"count 9998.000000\n",
"mean 0.239161\n",
"std 0.258047\n",
"min 0.018704\n",
"25% 0.064364\n",
"50% 0.113151\n",
"75% 0.279245\n",
"max 0.923141"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(9999, 36)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\"small_click.csv\")\n",
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['article_type', 'cid', 'cid_id', 'cid_type', 'city_id',\n",
" 'click_count_choice', 'content_level', 'created_time', 'device_id',\n",
" 'device_type', 'device_view', 'diary_doctor_id', 'diary_new_favor',\n",
" 'diary_new_replies', 'diary_new_topic_replies', 'diary_new_topic_votes',\n",
" 'diary_new_topics', 'diary_service_id', 'diary_updated_time',\n",
" 'is_recommend', 'live_fake_max_num', 'live_is_finish',\n",
" 'live_max_view_num', 'live_replay_danmu', 'live_topic_id', 'new_votes',\n",
" 'page_view', 'question_answer_reply_num', 'reply_num', 'reply_vote_num',\n",
" 'show_count', 'show_count_choice', 'stat_date', 'time', 'user_view',\n",
" 'label'],\n",
" dtype='object')"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>cid</th>\n",
" </tr>\n",
" <tr>\n",
" <th>device_id</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0027137D-E16E-4BB1-9FC6-2EDA44FF1F5C</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0073F6BD-F93B-46D6-AE4F-46F70B5A7665</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0074C249-33DA-457E-8960-3B98DC8887C6</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008796749543200</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008796752520863</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008796762134609</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>008AEF54-E367-475D-9614-27830B1AB6D1</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>00981796-12AE-4BDE-853C-A39037A5F8CE</th>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>00BAD771-8FDA-4739-AE10-78A708C97E8A</th>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>00CA20EB-2719-4518-85CC-60E765AC526F</th>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01126351-2DB2-4F39-B310-71783A03EE1C</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01188F61-0B48-41C7-A45A-7581A9D6EE48</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>013738A2-5886-48B5-A0C4-BF849B411CAC</th>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>014512241593985</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0155A2C3-FCBD-4248-8761-2F8D0AFEA49C</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>015C9051-1B61-4E10-AA29-32D989BBFE88</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01993D28-5D0A-4C8B-87B5-02211AA4E2C1</th>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01B86BB8-1A0C-40D3-9103-365A3A3498D6</th>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01CAA461-91AD-417E-9D75-AF8854F63A98</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>01E35E1F-CAAF-42A0-A858-B545BD1C4455</th>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0241469B-967E-4445-AC8B-A9218771640A</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02754D73-5343-40B9-9DFF-43B04AC18A9F</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02B1800B-E29D-4899-95B6-A83CD8AD0954</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02C3201E-7A3C-4A94-972E-846036ECA970</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02C505F6-5186-4489-B478-823330FD4FA5</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02C744A4-90B9-43E4-ABA8-46560B2715AC</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>02CB8A9D-CE29-403F-A87F-8C0245BCC804</th>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>030C3E1A-155C-47C4-8BE8-6BC20DCA3FD1</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>031FCF2A-8F5E-4312-BF48-E9F8F4710BD6</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>033B1FFB-31BA-4179-AC33-1369F1B21748</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e3b37c0f2ec18806</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e6a79883ab24c033</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e72d5572556a768a</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e7e288fc31427833</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e87d7b652273fb84</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_e96b1117a08027c1</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_eb04dfe8020c4abf</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ec0d18f354bd4650</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ed37d88b405eba00</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_edd61267a99e4981</th>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_eddfd121ccfc308c</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ee4b1688ecb46676</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_ee97be7ea5ef3417</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_efbfdb353bc23505</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f0f2132ee59a7fa4</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f1faded03ceab141</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f38ab0dba9bf1dd5</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f3e1cbf7fbd759f2</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f40916a405dc7ac5</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f515a007af34d7a</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f67e62bd514cfe32</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f6e89217fb8d4c86</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f7c24eb6908abdda</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f8554903cd899b8f</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_f91cecf0d12a1cdc</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fc3410e808b9c8b6</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fc508414e32d3989</th>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fd724c132e4fb908</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_fe5165a27249fd08</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>androidid_feba9a7d18f1054a</th>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>4318 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" cid\n",
"device_id \n",
"0027137D-E16E-4BB1-9FC6-2EDA44FF1F5C 1\n",
"0073F6BD-F93B-46D6-AE4F-46F70B5A7665 1\n",
"0074C249-33DA-457E-8960-3B98DC8887C6 1\n",
"008796749543200 1\n",
"008796752520863 1\n",
"008796762134609 1\n",
"008AEF54-E367-475D-9614-27830B1AB6D1 1\n",
"00981796-12AE-4BDE-853C-A39037A5F8CE 3\n",
"00BAD771-8FDA-4739-AE10-78A708C97E8A 9\n",
"00CA20EB-2719-4518-85CC-60E765AC526F 23\n",
"01126351-2DB2-4F39-B310-71783A03EE1C 4\n",
"01188F61-0B48-41C7-A45A-7581A9D6EE48 4\n",
"013738A2-5886-48B5-A0C4-BF849B411CAC 9\n",
"014512241593985 1\n",
"0155A2C3-FCBD-4248-8761-2F8D0AFEA49C 1\n",
"015C9051-1B61-4E10-AA29-32D989BBFE88 1\n",
"01993D28-5D0A-4C8B-87B5-02211AA4E2C1 3\n",
"01B86BB8-1A0C-40D3-9103-365A3A3498D6 5\n",
"01CAA461-91AD-417E-9D75-AF8854F63A98 1\n",
"01E35E1F-CAAF-42A0-A858-B545BD1C4455 3\n",
"0241469B-967E-4445-AC8B-A9218771640A 2\n",
"02754D73-5343-40B9-9DFF-43B04AC18A9F 1\n",
"02B1800B-E29D-4899-95B6-A83CD8AD0954 1\n",
"02C3201E-7A3C-4A94-972E-846036ECA970 1\n",
"02C505F6-5186-4489-B478-823330FD4FA5 1\n",
"02C744A4-90B9-43E4-ABA8-46560B2715AC 1\n",
"02CB8A9D-CE29-403F-A87F-8C0245BCC804 7\n",
"030C3E1A-155C-47C4-8BE8-6BC20DCA3FD1 2\n",
"031FCF2A-8F5E-4312-BF48-E9F8F4710BD6 2\n",
"033B1FFB-31BA-4179-AC33-1369F1B21748 1\n",
"... ...\n",
"androidid_e3b37c0f2ec18806 1\n",
"androidid_e6a79883ab24c033 1\n",
"androidid_e72d5572556a768a 1\n",
"androidid_e7e288fc31427833 2\n",
"androidid_e87d7b652273fb84 1\n",
"androidid_e96b1117a08027c1 1\n",
"androidid_eb04dfe8020c4abf 1\n",
"androidid_ec0d18f354bd4650 1\n",
"androidid_ed37d88b405eba00 1\n",
"androidid_edd61267a99e4981 5\n",
"androidid_eddfd121ccfc308c 1\n",
"androidid_ee4b1688ecb46676 2\n",
"androidid_ee97be7ea5ef3417 1\n",
"androidid_efbfdb353bc23505 1\n",
"androidid_f0f2132ee59a7fa4 1\n",
"androidid_f1faded03ceab141 4\n",
"androidid_f38ab0dba9bf1dd5 1\n",
"androidid_f3e1cbf7fbd759f2 2\n",
"androidid_f40916a405dc7ac5 1\n",
"androidid_f515a007af34d7a 2\n",
"androidid_f67e62bd514cfe32 1\n",
"androidid_f6e89217fb8d4c86 1\n",
"androidid_f7c24eb6908abdda 1\n",
"androidid_f8554903cd899b8f 2\n",
"androidid_f91cecf0d12a1cdc 1\n",
"androidid_fc3410e808b9c8b6 1\n",
"androidid_fc508414e32d3989 2\n",
"androidid_fd724c132e4fb908 1\n",
"androidid_fe5165a27249fd08 1\n",
"androidid_feba9a7d18f1054a 1\n",
"\n",
"[4318 rows x 1 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2 = df[[\"device_id\",\"cid\"]].groupby(\"device_id\").count()\n",
"df2"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x10b49cb38>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"df2.boxplot()\n",
"plt.ylabel(\"ARI\")\n",
"plt.xlabel(\"Dissimilarity Measures\")#我们设置横纵坐标的标题。\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data_a={'state':[1,1,2],'pop':['a','b','c']}\n",
"data_b={'state':[1,2,3],'pop':['b','c','d']}\n",
"a=pd.DataFrame(data_a)\n",
"b=pd.DataFrame(data_b) "
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 a 1\n",
"1 b 1\n",
"2 c 2"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"b"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"a = a.append(b);a = a.append(b)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>d</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 a 1\n",
"1 b 1\n",
"2 c 2\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3\n",
"0 b 1\n",
"1 c 2\n",
"2 d 3"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"result = a.drop_duplicates(subset=['pop','state'],keep=False)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pop</th>\n",
" <th>state</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pop state\n",
"0 a 1"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"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": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment
