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

Standardized on df as the DataFrame variable for code snippets.

Browse Source
This commit is contained in:
Donne Martin 2015-01-31 08:00:08 -05:00
parent 45634da9ff
commit ebe737d11e
1 changed files with 65 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

130
pandas/pandas.ipynb
View File

@ -1,7 +1,7 @@
{
"metadata": {
"name": "",
"signature": "sha256:56fea349850ffa0f72e6b8900647ed0f5ede765deae5932b1a26237f03166107"
"signature": "sha256:4c3e3bc5e2e66a53e95dce82d5f14b65d389cff01d434f1cf65ee91981716551"
},
"nbformat": 3,
"nbformat_minor": 0,
@ -588,11 +588,11 @@
"cell_type": "code",
"collapsed": false,
"input": [
"data_1 = {'state': ['VA', 'VA', 'VA', 'MD', 'MD'],\n",
" 'year': [2012, 2013, 2014, 2014, 2015],\n",
" 'pop': [5.0, 5.1, 5.2, 4.0, 4.1]}\n",
"frame_1 = DataFrame(data_1)\n",
"frame_1"
"data_1 = {'state' : ['VA', 'VA', 'VA', 'MD', 'MD'],\n",
" 'year' : [2012, 2013, 2014, 2014, 2015],\n",
" 'pop' : [5.0, 5.1, 5.2, 4.0, 4.1]}\n",
"df_1 = DataFrame(data_1)\n",
"df_1"
],
"language": "python",
"metadata": {},
@ -670,8 +670,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_2 = DataFrame(data_1, columns=['year', 'state', 'pop'])\n",
"frame_2"
"df_2 = DataFrame(data_1, columns=['year', 'state', 'pop'])\n",
"df_2"
],
"language": "python",
"metadata": {},
@ -749,8 +749,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3 = DataFrame(data_1, columns=['year', 'state', 'pop', 'unempl'])\n",
"frame_3"
"df_3 = DataFrame(data_1, columns=['year', 'state', 'pop', 'unempl'])\n",
"df_3"
],
"language": "python",
"metadata": {},
@ -834,7 +834,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3['state']"
"df_3['state']"
],
"language": "python",
"metadata": {},
@ -866,7 +866,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3.year"
"df_3.year"
],
"language": "python",
"metadata": {},
@ -898,7 +898,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3.ix[0]"
"df_3.ix[0]"
],
"language": "python",
"metadata": {},
@ -929,8 +929,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3['unempl'] = np.arange(5)\n",
"frame_3"
"df_3['unempl'] = np.arange(5)\n",
"df_3"
],
"language": "python",
"metadata": {},
@ -1015,8 +1015,8 @@
"collapsed": false,
"input": [
"unempl = Series([6.0, 6.0, 6.1], index=[2, 3, 4])\n",
"frame_3['unempl'] = unempl\n",
"frame_3"
"df_3['unempl'] = unempl\n",
"df_3"
],
"language": "python",
"metadata": {},
@ -1100,8 +1100,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3['state_dup'] = frame_3['state']\n",
"frame_3"
"df_3['state_dup'] = df_3['state']\n",
"df_3"
],
"language": "python",
"metadata": {},
@ -1191,8 +1191,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"del frame_3['state_dup']\n",
"frame_3"
"del df_3['state_dup']\n",
"df_3"
],
"language": "python",
"metadata": {},
@ -1278,8 +1278,8 @@
"input": [
"pop = {'VA' : {2013 : 5.1, 2014 : 5.2},\n",
" 'MD' : {2014 : 4.0, 2015 : 4.1}}\n",
"frame_4 = DataFrame(pop)\n",
"frame_4"
"df_4 = DataFrame(pop)\n",
"df_4"
],
"language": "python",
"metadata": {},
@ -1339,7 +1339,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_4.T"
"df_4.T"
],
"language": "python",
"metadata": {},
@ -1396,10 +1396,10 @@
"cell_type": "code",
"collapsed": false,
"input": [
"data_2 = {'VA' : frame_4['VA'][1:],\n",
" 'MD' : frame_4['MD'][2:]}\n",
"frame_5 = DataFrame(data_2)\n",
"frame_5"
"data_2 = {'VA' : df_4['VA'][1:],\n",
" 'MD' : df_4['MD'][2:]}\n",
"df_5 = DataFrame(data_2)\n",
"df_5"
],
"language": "python",
"metadata": {},
@ -1453,8 +1453,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_5.index.name = 'year'\n",
"frame_5"
"df_5.index.name = 'year'\n",
"df_5"
],
"language": "python",
"metadata": {},
@ -1514,8 +1514,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_5.columns.name = 'state'\n",
"frame_5"
"df_5.columns.name = 'state'\n",
"df_5"
],
"language": "python",
"metadata": {},
@ -1575,7 +1575,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_5.values"
"df_5.values"
],
"language": "python",
"metadata": {},
@ -1603,7 +1603,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3.values"
"df_3.values"
],
"language": "python",
"metadata": {},
@ -1641,7 +1641,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3"
"df_3"
],
"language": "python",
"metadata": {},
@ -1725,7 +1725,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3.reindex(list(reversed(range(0, 6))))"
"df_3.reindex(list(reversed(range(0, 6))))"
],
"language": "python",
"metadata": {},
@ -1817,7 +1817,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3.reindex(range(6, 0), fill_value=0)"
"df_3.reindex(range(6, 0), fill_value=0)"
],
"language": "python",
"metadata": {},
@ -1931,7 +1931,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3.reindex(columns=['state', 'pop', 'unempl', 'year'])"
"df_3.reindex(columns=['state', 'pop', 'unempl', 'year'])"
],
"language": "python",
"metadata": {},
@ -2015,9 +2015,9 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_3.reindex(index=list(reversed(range(0, 6))),\n",
" fill_value=0,\n",
" columns=['state', 'pop', 'unempl', 'year'])"
"df_3.reindex(index=list(reversed(range(0, 6))),\n",
" fill_value=0,\n",
" columns=['state', 'pop', 'unempl', 'year'])"
],
"language": "python",
"metadata": {},
@ -2109,8 +2109,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6 = frame_3.ix[range(0, 7), ['state', 'pop', 'unempl', 'year']]\n",
"frame_6"
"df_6 = df_3.ix[range(0, 7), ['state', 'pop', 'unempl', 'year']]\n",
"df_6"
],
"language": "python",
"metadata": {},
@ -2217,8 +2217,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_7 = frame_6.drop([0, 1])\n",
"frame_7"
"df_7 = df_6.drop([0, 1])\n",
"df_7"
],
"language": "python",
"metadata": {},
@ -2302,8 +2302,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_7 = frame_7.drop('unempl', axis=1)\n",
"frame_7"
"df_7 = df_7.drop('unempl', axis=1)\n",
"df_7"
],
"language": "python",
"metadata": {},
@ -2599,7 +2599,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6"
"df_6"
],
"language": "python",
"metadata": {},
@ -2699,7 +2699,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6[['pop', 'unempl']]"
"df_6[['pop', 'unempl']]"
],
"language": "python",
"metadata": {},
@ -2783,7 +2783,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6[:2]"
"df_6[:2]"
],
"language": "python",
"metadata": {},
@ -2843,7 +2843,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6[frame_6['pop'] > 5]"
"df_6[df_6['pop'] > 5]"
],
"language": "python",
"metadata": {},
@ -2903,7 +2903,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6 > 5"
"df_6 > 5"
],
"language": "python",
"metadata": {},
@ -3003,7 +3003,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6[frame_6 > 5]"
"df_6[df_6 > 5]"
],
"language": "python",
"metadata": {},
@ -3103,7 +3103,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6.ix[2:3]"
"df_6.ix[2:3]"
],
"language": "python",
"metadata": {},
@ -3163,8 +3163,8 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6.ix[0:2, 'pop']\n",
"frame_6"
"df_6.ix[0:2, 'pop']\n",
"df_6"
],
"language": "python",
"metadata": {},
@ -3264,7 +3264,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_6.ix[frame_6.unempl > 5.0]"
"df_6.ix[df_6.unempl > 5.0]"
],
"language": "python",
"metadata": {},
@ -3457,9 +3457,9 @@
"collapsed": false,
"input": [
"np.random.seed(0)\n",
"frame_8 = DataFrame(np.random.rand(9).reshape((3, 3)),\n",
" columns=['a', 'b', 'c'])\n",
"frame_8"
"df_8 = DataFrame(np.random.rand(9).reshape((3, 3)),\n",
" columns=['a', 'b', 'c'])\n",
"df_8"
],
"language": "python",
"metadata": {},
@ -3517,9 +3517,9 @@
"collapsed": false,
"input": [
"np.random.seed(1)\n",
"frame_9 = DataFrame(np.random.rand(9).reshape((3, 3)),\n",
" columns=['b', 'c', 'd'])\n",
"frame_9"
"df_9 = DataFrame(np.random.rand(9).reshape((3, 3)),\n",
" columns=['b', 'c', 'd'])\n",
"df_9"
],
"language": "python",
"metadata": {},
@ -3583,7 +3583,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_8 + frame_9"
"df_8 + df_9"
],
"language": "python",
"metadata": {},
@ -3651,7 +3651,7 @@
"cell_type": "code",
"collapsed": false,
"input": [
"frame_8.add(frame_9, fill_value=0)"
"df_8.add(df_9, fill_value=0)"
],
"language": "python",
"metadata": {},