StarMirror/data-science-ipython-notebooks
1
0
Fork 0
mirror of https://github.com/donnemartin/data-science-ipython-notebooks.git synced 2024-03-22 13:30:56 +08:00
Code Issues Projects Releases Wiki Activity

Added snippet to concatenate two DataFrames.

Browse Source
This commit is contained in:
Donne Martin 2015-02-13 15:53:15 -05:00
parent 90baf301b6
commit c7bc8e386f
1 changed files with 203 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

208
pandas/pandas_clean.ipynb
View File

@ -1,7 +1,7 @@
{
"metadata": {
"name": "",
"signature": "sha256:82be3772f18b2c96a1486b76adf812e774890e366b350dfd5b1257ab4b086b8e"
"signature": "sha256:f776a525b9cd73f2f19e9e51e3318238aa9c122bb94228ae307286d483a6c2f1"
},
"nbformat": 3,
"nbformat_minor": 0,
@ -301,13 +301,13 @@
" <tr>\n",
" <th>3</th>\n",
" <td> 4.0</td>\n",
" <td> MARYLAND</td>\n",
" <td> MD</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 4.1</td>\n",
" <td> MARYLAND</td>\n",
" <td> MD</td>\n",
" <td> 2015</td>\n",
" </tr>\n",
" </tbody>\n",
@ -322,12 +322,210 @@
"0 5.0 VIRGINIA 2012\n",
"1 5.1 VIRGINIA 2013\n",
"2 5.2 VIRGINIA 2014\n",
"3 4.0 MARYLAND 2014\n",
"4 4.1 MARYLAND 2015"
"3 4.0 MD 2014\n",
"4 4.1 MD 2015"
]
}
],
"prompt_number": 5
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Concatenate two DataFrames:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data_2 = {'state' : ['NY', 'NY', 'NY', 'FL', 'FL'],\n",
" 'year' : [2012, 2013, 2014, 2014, 2015],\n",
" 'pop' : [6.0, 6.1, 6.2, 3.0, 3.1]}\n",
"df_2 = DataFrame(data_2)\n",
"df_2"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\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",
" <th>year</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 6.0</td>\n",
" <td> NY</td>\n",
" <td> 2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 6.1</td>\n",
" <td> NY</td>\n",
" <td> 2013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 6.2</td>\n",
" <td> NY</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 3.0</td>\n",
" <td> FL</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 3.1</td>\n",
" <td> FL</td>\n",
" <td> 2015</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 6,
"text": [
" pop state year\n",
"0 6.0 NY 2012\n",
"1 6.1 NY 2013\n",
"2 6.2 NY 2014\n",
"3 3.0 FL 2014\n",
"4 3.1 FL 2015"
]
}
],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"df_3 = pd.concat([df_1, df_2])\n",
"df_3"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\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",
" <th>year</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 5.0</td>\n",
" <td> VIRGINIA</td>\n",
" <td> 2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 5.1</td>\n",
" <td> VIRGINIA</td>\n",
" <td> 2013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 5.2</td>\n",
" <td> VIRGINIA</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 4.0</td>\n",
" <td> MD</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 4.1</td>\n",
" <td> MD</td>\n",
" <td> 2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 6.0</td>\n",
" <td> NY</td>\n",
" <td> 2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 6.1</td>\n",
" <td> NY</td>\n",
" <td> 2013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 6.2</td>\n",
" <td> NY</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 3.0</td>\n",
" <td> FL</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 3.1</td>\n",
" <td> FL</td>\n",
" <td> 2015</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 7,
"text": [
" pop state year\n",
"0 5.0 VIRGINIA 2012\n",
"1 5.1 VIRGINIA 2013\n",
"2 5.2 VIRGINIA 2014\n",
"3 4.0 MD 2014\n",
"4 4.1 MD 2015\n",
"0 6.0 NY 2012\n",
"1 6.1 NY 2013\n",
"2 6.2 NY 2014\n",
"3 3.0 FL 2014\n",
"4 3.1 FL 2015"
]
}
],
"prompt_number": 7
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 7
}
],
"metadata": {}