balkian/sitc
1
0
Fork 0
mirror of https://github.com/gsi-upm/sitc synced 2024-11-22 06:22:29 +00:00
Code Issues Releases Wiki Activity

Merge branch 'master' of github.com:gsi-upm/sitc

Browse Source
This commit is contained in:
Oscar Araque 2017-03-27 19:48:41 +02:00
commit cc63d9ba79
1 changed files with 15 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
ml2/3_5_Exercise_1.ipynb
View File

@ -46,7 +46,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 2,
"metadata": { "metadata": {
"collapsed": true "collapsed": true
}, },
@ -83,7 +83,7 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": { "metadata": {
"collapsed": true "collapsed": false
}, },
"outputs": [], "outputs": [],
"source": [] "source": []
@ -420,11 +420,11 @@
"source": [ "source": [
"# Group ages to simplify machine learning algorithms. 0: 0-5, 1: 6-10, 2: 11-15, 3: 16-59 and 4: 60-80\n", "# Group ages to simplify machine learning algorithms. 0: 0-5, 1: 6-10, 2: 11-15, 3: 16-59 and 4: 60-80\n",
"df['AgeGroup'] = 0\n", "df['AgeGroup'] = 0\n",
"df.loc[(.AgeFill<6),'AgeGroup'] = 0\n", "df.loc[(.Age<6),'AgeGroup'] = 0\n",
"df.loc[(df.AgeFill>=6) & (df.AgeFill < 11),'AgeGroup'] = 1\n", "df.loc[(df.Age>=6) & (df.Age < 11),'AgeGroup'] = 1\n",
"df.loc[(df.AgeFill>=11) & (df.AgeFill < 16),'AgeGroup'] = 2\n", "df.loc[(df.Age>=11) & (df.Age < 16),'AgeGroup'] = 2\n",
"df.loc[(df.AgeFill>=16) & (df.AgeFill < 60),'AgeGroup'] = 3\n", "df.loc[(df.Age>=16) & (df.Age < 60),'AgeGroup'] = 3\n",
"df.loc[(df.AgeFill>=60),'AgeGroup'] = 4" "df.loc[(df.Age>=60),'AgeGroup'] = 4"
] ]
}, },
{ {
@ -437,18 +437,22 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 8,
"metadata": { "metadata": {
"collapsed": false "collapsed": false
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"def substrings_in_string(big_string, substrings):\n", "def substrings_in_string(big_string, substrings):\n",
" if type(big_string) == float:\n",
" if np.isnan(big_string):\n",
" return 'X'\n",
" for substring in substrings:\n", " for substring in substrings:\n",
" if big_string.find(substring) != 1:\n", " if big_string.find(substring) != 1:\n",
" return substring\n", " return substring\n",
" print(big_string)\n", " print(big_string)\n",
" return np.nan\n", " return 'X'\n",
" \n",
"#Turning cabin number into Deck\n", "#Turning cabin number into Deck\n",
"cabin_list = ['A', 'B', 'C', 'D', 'E', 'F', 'T', 'G', 'Unknown']\n", "cabin_list = ['A', 'B', 'C', 'D', 'E', 'F', 'T', 'G', 'Unknown']\n",
"df['Deck']=df['Cabin'].map(lambda x: substrings_in_string(x, cabin_list))" "df['Deck']=df['Cabin'].map(lambda x: substrings_in_string(x, cabin_list))"
@ -537,7 +541,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.5.1+" "version": "3.5.2"
} }
}, },
"nbformat": 4, "nbformat": 4,