arthur/handson-ml3
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/handson-ml3.git synced 2026-01-14 12:14:36 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update to latest library versions

Browse Source
This commit is contained in:
Aurélien Geron
2020-11-21 12:22:42 +13:00
parent 1e81324573
commit f225f59780
3 changed files with 224 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

161
02_end_to_end_machine_learning_project.ipynb
View File

@@ -931,7 +931,7 @@
"rooms_ix, bedrooms_ix, population_ix, households_ix = 3, 4, 5, 6\n",
"\n",
"class CombinedAttributesAdder(BaseEstimator, TransformerMixin):\n",
" def __init__(self, add_bedrooms_per_room = True): # no *args or **kargs\n",
" def __init__(self, add_bedrooms_per_room=True): # no *args or **kargs\n",
" self.add_bedrooms_per_room = add_bedrooms_per_room\n",
" def fit(self, X, y=None):\n",
" return self # nothing else to do\n",
@@ -949,11 +949,36 @@
"housing_extra_attribs = attr_adder.transform(housing.values)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note that I hard coded the indices (3, 4, 5, 6) for concision and clarity in the book, but it would be much cleaner to get them dynamically, like this:"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {},
"outputs": [],
"source": [
"col_names = \"total_rooms\", \"total_bedrooms\", \"population\", \"households\"\n",
"rooms_ix, bedrooms_ix, population_ix, households_ix = [\n",
" housing.columns.get_loc(c) for c in col_names] # get the column indices"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Also, `housing_extra_attribs` is a NumPy array, we've lost the column names (unfortunately, that's a problem with Scikit-Learn). To recover a `DataFrame`, you could run this:"
]
},
{
"cell_type": "code",
"execution_count": 72,
"metadata": {},
"outputs": [],
"source": [
"housing_extra_attribs = pd.DataFrame(\n",
" housing_extra_attribs,\n",
@@ -971,7 +996,7 @@
},
{
"cell_type": "code",
"execution_count": 72,
"execution_count": 73,
"metadata": {},
"outputs": [],
"source": [
@@ -989,7 +1014,7 @@
},
{
"cell_type": "code",
"execution_count": 73,
"execution_count": 74,
"metadata": {},
"outputs": [],
"source": [
@@ -998,7 +1023,7 @@
},
{
"cell_type": "code",
"execution_count": 74,
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": [
@@ -1017,7 +1042,7 @@
},
{
"cell_type": "code",
"execution_count": 75,
"execution_count": 76,
"metadata": {},
"outputs": [],
"source": [
@@ -1026,7 +1051,7 @@
},
{
"cell_type": "code",
"execution_count": 76,
"execution_count": 77,
"metadata": {},
"outputs": [],
"source": [
@@ -1042,7 +1067,7 @@
},
{
"cell_type": "code",
"execution_count": 77,
"execution_count": 78,
"metadata": {},
"outputs": [],
"source": [
@@ -1067,7 +1092,7 @@
},
{
"cell_type": "code",
"execution_count": 78,
"execution_count": 79,
"metadata": {},
"outputs": [],
"source": [
@@ -1089,7 +1114,7 @@
},
{
"cell_type": "code",
"execution_count": 79,
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
@@ -1103,7 +1128,7 @@
},
{
"cell_type": "code",
"execution_count": 80,
"execution_count": 81,
"metadata": {},
"outputs": [],
"source": [
@@ -1120,7 +1145,7 @@
},
{
"cell_type": "code",
"execution_count": 81,
"execution_count": 82,
"metadata": {},
"outputs": [],
"source": [
@@ -1136,7 +1161,7 @@
},
{
"cell_type": "code",
"execution_count": 82,
"execution_count": 83,
"metadata": {},
"outputs": [],
"source": [
@@ -1148,7 +1173,7 @@
},
{
"cell_type": "code",
"execution_count": 83,
"execution_count": 84,
"metadata": {},
"outputs": [],
"source": [
@@ -1169,7 +1194,7 @@
},
{
"cell_type": "code",
"execution_count": 84,
"execution_count": 85,
"metadata": {},
"outputs": [],
"source": [
@@ -1178,7 +1203,7 @@
},
{
"cell_type": "code",
"execution_count": 85,
"execution_count": 86,
"metadata": {},
"outputs": [],
"source": [
@@ -1187,7 +1212,7 @@
},
{
"cell_type": "code",
"execution_count": 86,
"execution_count": 87,
"metadata": {},
"outputs": [],
"source": [
@@ -1201,7 +1226,7 @@
},
{
"cell_type": "code",
"execution_count": 87,
"execution_count": 88,
"metadata": {},
"outputs": [],
"source": [
@@ -1213,7 +1238,7 @@
},
{
"cell_type": "code",
"execution_count": 88,
"execution_count": 89,
"metadata": {},
"outputs": [],
"source": [
@@ -1225,7 +1250,7 @@
},
{
"cell_type": "code",
"execution_count": 89,
"execution_count": 90,
"metadata": {},
"outputs": [],
"source": [
@@ -1244,7 +1269,7 @@
},
{
"cell_type": "code",
"execution_count": 90,
"execution_count": 91,
"metadata": {},
"outputs": [],
"source": [
@@ -1257,7 +1282,7 @@
},
{
"cell_type": "code",
"execution_count": 91,
"execution_count": 92,
"metadata": {},
"outputs": [],
"source": [
@@ -1271,7 +1296,7 @@
},
{
"cell_type": "code",
"execution_count": 92,
"execution_count": 93,
"metadata": {},
"outputs": [],
"source": [
@@ -1290,7 +1315,7 @@
},
{
"cell_type": "code",
"execution_count": 93,
"execution_count": 94,
"metadata": {},
"outputs": [],
"source": [
@@ -1302,7 +1327,7 @@
},
{
"cell_type": "code",
"execution_count": 94,
"execution_count": 95,
"metadata": {},
"outputs": [],
"source": [
@@ -1314,7 +1339,7 @@
},
{
"cell_type": "code",
"execution_count": 95,
"execution_count": 96,
"metadata": {},
"outputs": [],
"source": [
@@ -1328,7 +1353,7 @@
},
{
"cell_type": "code",
"execution_count": 96,
"execution_count": 97,
"metadata": {},
"outputs": [],
"source": [
@@ -1338,7 +1363,7 @@
},
{
"cell_type": "code",
"execution_count": 97,
"execution_count": 98,
"metadata": {},
"outputs": [],
"source": [
@@ -1354,7 +1379,7 @@
},
{
"cell_type": "code",
"execution_count": 98,
"execution_count": 99,
"metadata": {},
"outputs": [],
"source": [
@@ -1384,7 +1409,7 @@
},
{
"cell_type": "code",
"execution_count": 99,
"execution_count": 100,
"metadata": {},
"outputs": [],
"source": [
@@ -1393,7 +1418,7 @@
},
{
"cell_type": "code",
"execution_count": 100,
"execution_count": 101,
"metadata": {},
"outputs": [],
"source": [
@@ -1409,7 +1434,7 @@
},
{
"cell_type": "code",
"execution_count": 101,
"execution_count": 102,
"metadata": {},
"outputs": [],
"source": [
@@ -1420,7 +1445,7 @@
},
{
"cell_type": "code",
"execution_count": 102,
"execution_count": 103,
"metadata": {},
"outputs": [],
"source": [
@@ -1429,7 +1454,7 @@
},
{
"cell_type": "code",
"execution_count": 103,
"execution_count": 104,
"metadata": {},
"outputs": [],
"source": [
@@ -1449,7 +1474,7 @@
},
{
"cell_type": "code",
"execution_count": 104,
"execution_count": 105,
"metadata": {},
"outputs": [],
"source": [
@@ -1460,7 +1485,7 @@
},
{
"cell_type": "code",
"execution_count": 105,
"execution_count": 106,
"metadata": {},
"outputs": [],
"source": [
@@ -1470,7 +1495,7 @@
},
{
"cell_type": "code",
"execution_count": 106,
"execution_count": 107,
"metadata": {},
"outputs": [],
"source": [
@@ -1484,7 +1509,7 @@
},
{
"cell_type": "code",
"execution_count": 107,
"execution_count": 108,
"metadata": {},
"outputs": [],
"source": [
@@ -1502,7 +1527,7 @@
},
{
"cell_type": "code",
"execution_count": 108,
"execution_count": 109,
"metadata": {},
"outputs": [],
"source": [
@@ -1518,7 +1543,7 @@
},
{
"cell_type": "code",
"execution_count": 109,
"execution_count": 110,
"metadata": {},
"outputs": [],
"source": [
@@ -1540,7 +1565,7 @@
},
{
"cell_type": "code",
"execution_count": 110,
"execution_count": 111,
"metadata": {},
"outputs": [],
"source": [
@@ -1560,7 +1585,7 @@
},
{
"cell_type": "code",
"execution_count": 111,
"execution_count": 112,
"metadata": {},
"outputs": [],
"source": [
@@ -1585,7 +1610,7 @@
},
{
"cell_type": "code",
"execution_count": 112,
"execution_count": 113,
"metadata": {},
"outputs": [],
"source": [
@@ -1607,7 +1632,7 @@
},
{
"cell_type": "code",
"execution_count": 113,
"execution_count": 114,
"metadata": {},
"outputs": [],
"source": [
@@ -1616,7 +1641,7 @@
},
{
"cell_type": "code",
"execution_count": 114,
"execution_count": 115,
"metadata": {},
"outputs": [],
"source": [
@@ -1635,7 +1660,7 @@
},
{
"cell_type": "code",
"execution_count": 115,
"execution_count": 116,
"metadata": {},
"outputs": [],
"source": [
@@ -1671,7 +1696,7 @@
},
{
"cell_type": "code",
"execution_count": 116,
"execution_count": 117,
"metadata": {},
"outputs": [],
"source": [
@@ -1697,7 +1722,7 @@
},
{
"cell_type": "code",
"execution_count": 117,
"execution_count": 118,
"metadata": {},
"outputs": [],
"source": [
@@ -1715,7 +1740,7 @@
},
{
"cell_type": "code",
"execution_count": 118,
"execution_count": 119,
"metadata": {},
"outputs": [],
"source": [
@@ -1745,7 +1770,7 @@
},
{
"cell_type": "code",
"execution_count": 119,
"execution_count": 120,
"metadata": {},
"outputs": [],
"source": [
@@ -1778,7 +1803,7 @@
},
{
"cell_type": "code",
"execution_count": 120,
"execution_count": 121,
"metadata": {},
"outputs": [],
"source": [
@@ -1796,7 +1821,7 @@
},
{
"cell_type": "code",
"execution_count": 121,
"execution_count": 122,
"metadata": {},
"outputs": [],
"source": [
@@ -1819,7 +1844,7 @@
},
{
"cell_type": "code",
"execution_count": 122,
"execution_count": 123,
"metadata": {},
"outputs": [],
"source": [
@@ -1844,7 +1869,7 @@
},
{
"cell_type": "code",
"execution_count": 123,
"execution_count": 124,
"metadata": {},
"outputs": [],
"source": [
@@ -1883,7 +1908,7 @@
},
{
"cell_type": "code",
"execution_count": 124,
"execution_count": 125,
"metadata": {},
"outputs": [],
"source": [
@@ -1919,7 +1944,7 @@
},
{
"cell_type": "code",
"execution_count": 125,
"execution_count": 126,
"metadata": {},
"outputs": [],
"source": [
@@ -1935,7 +1960,7 @@
},
{
"cell_type": "code",
"execution_count": 126,
"execution_count": 127,
"metadata": {},
"outputs": [],
"source": [
@@ -1945,7 +1970,7 @@
},
{
"cell_type": "code",
"execution_count": 127,
"execution_count": 128,
"metadata": {},
"outputs": [],
"source": [
@@ -1961,7 +1986,7 @@
},
{
"cell_type": "code",
"execution_count": 128,
"execution_count": 129,
"metadata": {},
"outputs": [],
"source": [
@@ -1977,7 +2002,7 @@
},
{
"cell_type": "code",
"execution_count": 129,
"execution_count": 130,
"metadata": {},
"outputs": [],
"source": [
@@ -1989,7 +2014,7 @@
},
{
"cell_type": "code",
"execution_count": 130,
"execution_count": 131,
"metadata": {},
"outputs": [],
"source": [
@@ -2005,7 +2030,7 @@
},
{
"cell_type": "code",
"execution_count": 131,
"execution_count": 132,
"metadata": {},
"outputs": [],
"source": [
@@ -2021,7 +2046,7 @@
},
{
"cell_type": "code",
"execution_count": 132,
"execution_count": 133,
"metadata": {},
"outputs": [],
"source": [
@@ -2051,7 +2076,7 @@
},
{
"cell_type": "code",
"execution_count": 133,
"execution_count": 134,
"metadata": {},
"outputs": [],
"source": [
@@ -2064,7 +2089,7 @@
},
{
"cell_type": "code",
"execution_count": 134,
"execution_count": 135,
"metadata": {},
"outputs": [],
"source": [
@@ -2080,7 +2105,7 @@
},
{
"cell_type": "code",
"execution_count": 135,
"execution_count": 136,
"metadata": {},
"outputs": [],
"source": [
@@ -2114,7 +2139,7 @@
},
{
"cell_type": "code",
"execution_count": 136,
"execution_count": 137,
"metadata": {},
"outputs": [],
"source": [
@@ -2130,7 +2155,7 @@
},
{
"cell_type": "code",
"execution_count": 137,
"execution_count": 138,
"metadata": {},
"outputs": [],
"source": [
@@ -2168,7 +2193,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.7.8"
},
"nav_menu": {
"height": "279px",