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 drop a column in a DataFrame. Renamed pop to population to avoid clashing with the DataFrame pop function.

Browse Source
This commit is contained in:
Donne Martin 2015-02-14 06:42:44 -05:00
parent f31a289eab
commit d6348012a4
1 changed files with 130 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

125
pandas/pandas_clean.ipynb
View File

@ -1,7 +1,7 @@
{ {
"metadata": { "metadata": {
"name": "", "name": "",
"signature": "sha256:1c8b7cab9b55eb5888612d0b5149649565c258456e73e61b039225439aa11502" "signature": "sha256:b619f1fd1f2d4495d6a2fe9d048c09b7319b119d4e10a5b2348f0ac6f380a27c"
}, },
"nbformat": 3, "nbformat": 3,
"nbformat_minor": 0, "nbformat_minor": 0,
@ -45,7 +45,7 @@
"input": [ "input": [
"data_1 = {'state' : ['VA', 'VA', 'VA', 'MD', 'MD'],\n", "data_1 = {'state' : ['VA', 'VA', 'VA', 'MD', 'MD'],\n",
" 'year' : [2012, 2013, 2014, 2014, 2015],\n", " 'year' : [2012, 2013, 2014, 2014, 2015],\n",
" 'pop' : [5.0, 5.1, 5.2, 4.0, 4.1]}\n", " 'population' : [5.0, 5.1, 5.2, 4.0, 4.1]}\n",
"df_1 = DataFrame(data_1)\n", "df_1 = DataFrame(data_1)\n",
"df_1" "df_1"
], ],
@ -59,7 +59,7 @@
" <thead>\n", " <thead>\n",
" <tr style=\"text-align: right;\">\n", " <tr style=\"text-align: right;\">\n",
" <th></th>\n", " <th></th>\n",
" <th>pop</th>\n", " <th>population</th>\n",
" <th>state</th>\n", " <th>state</th>\n",
" <th>year</th>\n", " <th>year</th>\n",
" </tr>\n", " </tr>\n",
@ -103,7 +103,7 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 2, "prompt_number": 2,
"text": [ "text": [
" pop state year\n", " population state year\n",
"0 5.0 VA 2012\n", "0 5.0 VA 2012\n",
"1 5.1 VA 2013\n", "1 5.1 VA 2013\n",
"2 5.2 VA 2014\n", "2 5.2 VA 2014\n",
@ -130,7 +130,7 @@
" <thead>\n", " <thead>\n",
" <tr style=\"text-align: right;\">\n", " <tr style=\"text-align: right;\">\n",
" <th></th>\n", " <th></th>\n",
" <th>pop</th>\n", " <th>population</th>\n",
" <th>state</th>\n", " <th>state</th>\n",
" <th>year</th>\n", " <th>year</th>\n",
" </tr>\n", " </tr>\n",
@ -162,7 +162,7 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 3, "prompt_number": 3,
"text": [ "text": [
" pop state year\n", " population state year\n",
"0 5.0 VA 2012\n", "0 5.0 VA 2012\n",
"1 5.1 VA 2013\n", "1 5.1 VA 2013\n",
"2 5.2 VA 2014" "2 5.2 VA 2014"
@ -195,7 +195,7 @@
" <thead>\n", " <thead>\n",
" <tr style=\"text-align: right;\">\n", " <tr style=\"text-align: right;\">\n",
" <th></th>\n", " <th></th>\n",
" <th>pop</th>\n", " <th>population</th>\n",
" <th>state</th>\n", " <th>state</th>\n",
" <th>year</th>\n", " <th>year</th>\n",
" </tr>\n", " </tr>\n",
@ -239,7 +239,7 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 4, "prompt_number": 4,
"text": [ "text": [
" pop state year\n", " population state year\n",
"0 5.0 VIRGINIA 2012\n", "0 5.0 VIRGINIA 2012\n",
"1 5.1 VIRGINIA 2013\n", "1 5.1 VIRGINIA 2013\n",
"2 5.2 VIRGINIA 2014\n", "2 5.2 VIRGINIA 2014\n",
@ -274,7 +274,7 @@
" <thead>\n", " <thead>\n",
" <tr style=\"text-align: right;\">\n", " <tr style=\"text-align: right;\">\n",
" <th></th>\n", " <th></th>\n",
" <th>pop</th>\n", " <th>population</th>\n",
" <th>state</th>\n", " <th>state</th>\n",
" <th>year</th>\n", " <th>year</th>\n",
" </tr>\n", " </tr>\n",
@ -318,7 +318,7 @@
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 5, "prompt_number": 5,
"text": [ "text": [
" pop state year\n", " population state year\n",
"0 5.0 VIRGINIA 2012\n", "0 5.0 VIRGINIA 2012\n",
"1 5.1 VIRGINIA 2013\n", "1 5.1 VIRGINIA 2013\n",
"2 5.2 VIRGINIA 2014\n", "2 5.2 VIRGINIA 2014\n",
@ -333,17 +333,14 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Concatenate two DataFrames:" "Drop the 'population' column and return a copy of the DataFrame:"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"data_2 = {'state' : ['NY', 'NY', 'NY', 'FL', 'FL'],\n", "df_2 = df_1.drop('population', axis=1)\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" "df_2"
], ],
"language": "python", "language": "python",
@ -356,7 +353,83 @@
" <thead>\n", " <thead>\n",
" <tr style=\"text-align: right;\">\n", " <tr style=\"text-align: right;\">\n",
" <th></th>\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> VIRGINIA</td>\n",
" <td> 2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> VIRGINIA</td>\n",
" <td> 2013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> VIRGINIA</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> MARYLAND</td>\n",
" <td> 2014</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> MARYLAND</td>\n",
" <td> 2015</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 6,
"text": [
" state year\n",
"0 VIRGINIA 2012\n",
"1 VIRGINIA 2013\n",
"2 VIRGINIA 2014\n",
"3 MARYLAND 2014\n",
"4 MARYLAND 2015"
]
}
],
"prompt_number": 6
},
{
"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",
" 'population' : [6.0, 6.1, 6.2, 3.0, 3.1]}\n",
"df_3 = DataFrame(data_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>population</th>\n",
" <th>state</th>\n", " <th>state</th>\n",
" <th>year</th>\n", " <th>year</th>\n",
" </tr>\n", " </tr>\n",
@ -398,9 +471,9 @@
], ],
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 6, "prompt_number": 7,
"text": [ "text": [
" pop state year\n", " population state year\n",
"0 6.0 NY 2012\n", "0 6.0 NY 2012\n",
"1 6.1 NY 2013\n", "1 6.1 NY 2013\n",
"2 6.2 NY 2014\n", "2 6.2 NY 2014\n",
@ -409,14 +482,14 @@
] ]
} }
], ],
"prompt_number": 6 "prompt_number": 7
}, },
{ {
"cell_type": "code", "cell_type": "code",
"collapsed": false, "collapsed": false,
"input": [ "input": [
"df_3 = pd.concat([df_1, df_2])\n", "df_4 = pd.concat([df_1, df_3])\n",
"df_3" "df_4"
], ],
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
@ -428,7 +501,7 @@
" <thead>\n", " <thead>\n",
" <tr style=\"text-align: right;\">\n", " <tr style=\"text-align: right;\">\n",
" <th></th>\n", " <th></th>\n",
" <th>pop</th>\n", " <th>population</th>\n",
" <th>state</th>\n", " <th>state</th>\n",
" <th>year</th>\n", " <th>year</th>\n",
" </tr>\n", " </tr>\n",
@ -500,9 +573,9 @@
], ],
"metadata": {}, "metadata": {},
"output_type": "pyout", "output_type": "pyout",
"prompt_number": 7, "prompt_number": 8,
"text": [ "text": [
" pop state year\n", " population state year\n",
"0 5.0 VIRGINIA 2012\n", "0 5.0 VIRGINIA 2012\n",
"1 5.1 VIRGINIA 2013\n", "1 5.1 VIRGINIA 2013\n",
"2 5.2 VIRGINIA 2014\n", "2 5.2 VIRGINIA 2014\n",
@ -516,7 +589,7 @@
] ]
} }
], ],
"prompt_number": 7 "prompt_number": 8
}, },
{ {
"cell_type": "code", "cell_type": "code",
@ -525,7 +598,7 @@
"language": "python", "language": "python",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"prompt_number": 7 "prompt_number": 8
} }
], ],
"metadata": {} "metadata": {}