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

Cleaned up notebook.

Browse Source
This commit is contained in:
Donne Martin 2015-04-10 11:03:00 -04:00
parent 83cf7b1278
commit ad82bdeefc
1 changed files with 21 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

78
pandas/pandas_clean.ipynb
View File

@ -13,10 +13,8 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Pandas Cleaning\n", "# Pandas Cleaning\n",
"* Clean\n", "* Replace\n",
"* Transform\n", "* Drop\n",
"* Merge\n",
"* Reshape\n",
"* Concatenate" "* Concatenate"
] ]
}, },
@ -36,7 +34,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Check for matching values in a specific column for replacement:" "Setup a DataFrame:"
] ]
}, },
{ {
@ -115,61 +113,11 @@
"prompt_number": 2 "prompt_number": 2
}, },
{ {
"cell_type": "code", "cell_type": "markdown",
"collapsed": false,
"input": [
"df_1[df_1['state'] == 'VA']"
],
"language": "python",
"metadata": {}, "metadata": {},
"outputs": [ "source": [
{ "## Replace"
"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>population</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> VA</td>\n",
" <td> 2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 5.1</td>\n",
" <td> VA</td>\n",
" <td> 2013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 5.2</td>\n",
" <td> VA</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 3,
"text": [
" population state year\n",
"0 5.0 VA 2012\n",
"1 5.1 VA 2013\n",
"2 5.2 VA 2014"
] ]
}
],
"prompt_number": 3
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -329,6 +277,13 @@
], ],
"prompt_number": 5 "prompt_number": 5
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Drop"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
@ -402,6 +357,13 @@
], ],
"prompt_number": 6 "prompt_number": 6
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Concatenate"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},