diff --git a/.gitignore b/.gitignore
index c9a7a5183..5343563bc 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,4 @@
+models/
tmp/
*.bak
*.pkl
diff --git a/09_tabular.ipynb b/09_tabular.ipynb
index 18512daaf..e3fce47bd 100644
--- a/09_tabular.ipynb
+++ b/09_tabular.ipynb
@@ -286,7 +286,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -302,7 +302,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@@ -322,16 +322,16 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "Path('/home/sgugger/.fastai/archive/bluebook')"
+ "Path('/home/jhoward/.fastai/archive/bluebook')"
]
},
- "execution_count": null,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -343,7 +343,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
@@ -360,16 +360,16 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "(#7) [Path('Valid.csv'),Path('Machine_Appendix.csv'),Path('ValidSolution.csv'),Path('TrainAndValid.csv'),Path('random_forest_benchmark_test.csv'),Path('Test.csv'),Path('median_benchmark.csv')]"
+ "(#7) [Path('TrainAndValid.csv'),Path('Machine_Appendix.csv'),Path('random_forest_benchmark_test.csv'),Path('Test.csv'),Path('median_benchmark.csv'),Path('ValidSolution.csv'),Path('Valid.csv')]"
]
},
- "execution_count": null,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -415,7 +415,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
@@ -424,7 +424,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"metadata": {},
"outputs": [
{
@@ -446,7 +446,7 @@
" dtype='object')"
]
},
- "execution_count": null,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -466,7 +466,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
@@ -475,7 +475,7 @@
"array([nan, 'Medium', 'Small', 'Large / Medium', 'Mini', 'Large', 'Compact'], dtype=object)"
]
},
- "execution_count": null,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -493,7 +493,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
@@ -502,7 +502,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
@@ -521,7 +521,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
@@ -530,7 +530,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
@@ -615,7 +615,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
@@ -631,7 +631,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
@@ -648,16 +648,16 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "'saleYear saleMonth saleWeek saleDay saleDayofweek saleDayofyear saleIs_month_end saleIs_month_start saleIs_quarter_end saleIs_quarter_start saleIs_year_end saleIs_year_start saleElapsed'"
+ "'saleWeek saleYear saleMonth saleDay saleDayofweek saleDayofyear saleIs_month_end saleIs_month_start saleIs_quarter_end saleIs_quarter_start saleIs_year_end saleIs_year_start saleElapsed'"
]
},
- "execution_count": null,
+ "execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
@@ -694,7 +694,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
@@ -720,7 +720,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
@@ -740,7 +740,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
@@ -749,7 +749,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
@@ -765,7 +765,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 22,
"metadata": {},
"outputs": [
{
@@ -774,7 +774,7 @@
"(404710, 7988)"
]
},
- "execution_count": null,
+ "execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
@@ -792,7 +792,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 23,
"metadata": {},
"outputs": [
{
@@ -802,6 +802,7 @@
" \n",
" \n",
" | \n",
+ " saleWeek | \n",
" UsageBand | \n",
" fiModelDesc | \n",
" fiBaseModel | \n",
@@ -852,6 +853,7 @@
" saleIs_quarter_start | \n",
" saleIs_year_end | \n",
" saleIs_year_start | \n",
+ " saleElapsed | \n",
" auctioneerID_na | \n",
" MachineHoursCurrentMeter_na | \n",
" SalesID | \n",
@@ -863,17 +865,16 @@
" MachineHoursCurrentMeter | \n",
" saleYear | \n",
" saleMonth | \n",
- " saleWeek | \n",
" saleDay | \n",
" saleDayofweek | \n",
" saleDayofyear | \n",
- " saleElapsed | \n",
" SalePrice | \n",
"
\n",
" \n",
"
\n",
" \n",
" 0 | \n",
+ " 46 | \n",
" Low | \n",
" 521D | \n",
" 521 | \n",
@@ -924,26 +925,26 @@
" False | \n",
" False | \n",
" False | \n",
+ " 1163635200 | \n",
" False | \n",
" False | \n",
- " 1139246.0 | \n",
- " 999089.0 | \n",
- " 3157.0 | \n",
- " 121.0 | \n",
+ " 1139246 | \n",
+ " 999089 | \n",
+ " 3157 | \n",
+ " 121 | \n",
" 3.0 | \n",
- " 2004.0 | \n",
+ " 2004 | \n",
" 68.0 | \n",
- " 2006.0 | \n",
- " 11.0 | \n",
- " 46.0 | \n",
- " 16.0 | \n",
- " 3.0 | \n",
- " 320.0 | \n",
- " 1.163635e+09 | \n",
+ " 2006 | \n",
+ " 11 | \n",
+ " 16 | \n",
+ " 3 | \n",
+ " 320 | \n",
" 11.097410 | \n",
"
\n",
" \n",
" 1 | \n",
+ " 13 | \n",
" Low | \n",
" 950FII | \n",
" 950 | \n",
@@ -994,26 +995,26 @@
" False | \n",
" False | \n",
" False | \n",
+ " 1080259200 | \n",
" False | \n",
" False | \n",
- " 1139248.0 | \n",
- " 117657.0 | \n",
- " 77.0 | \n",
- " 121.0 | \n",
+ " 1139248 | \n",
+ " 117657 | \n",
+ " 77 | \n",
+ " 121 | \n",
" 3.0 | \n",
- " 1996.0 | \n",
+ " 1996 | \n",
" 4640.0 | \n",
- " 2004.0 | \n",
- " 3.0 | \n",
- " 13.0 | \n",
- " 26.0 | \n",
- " 4.0 | \n",
- " 86.0 | \n",
- " 1.080259e+09 | \n",
+ " 2004 | \n",
+ " 3 | \n",
+ " 26 | \n",
+ " 4 | \n",
+ " 86 | \n",
" 10.950807 | \n",
"
\n",
" \n",
" 2 | \n",
+ " 9 | \n",
" High | \n",
" 226 | \n",
" 226 | \n",
@@ -1064,22 +1065,21 @@
" False | \n",
" False | \n",
" False | \n",
+ " 1077753600 | \n",
" False | \n",
" False | \n",
- " 1139249.0 | \n",
- " 434808.0 | \n",
- " 7009.0 | \n",
- " 121.0 | \n",
+ " 1139249 | \n",
+ " 434808 | \n",
+ " 7009 | \n",
+ " 121 | \n",
" 3.0 | \n",
- " 2001.0 | \n",
+ " 2001 | \n",
" 2838.0 | \n",
- " 2004.0 | \n",
- " 2.0 | \n",
- " 9.0 | \n",
- " 26.0 | \n",
- " 3.0 | \n",
- " 57.0 | \n",
- " 1.077754e+09 | \n",
+ " 2004 | \n",
+ " 2 | \n",
+ " 26 | \n",
+ " 3 | \n",
+ " 57 | \n",
" 9.210340 | \n",
"
\n",
" \n",
@@ -1100,7 +1100,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 24,
"metadata": {},
"outputs": [
{
@@ -1168,7 +1168,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 25,
"metadata": {},
"outputs": [
{
@@ -1195,12 +1195,12 @@
" SalesID | \n",
" SalePrice | \n",
" MachineID | \n",
- " ModelID | \n",
+ " saleWeek | \n",
" ... | \n",
- " saleDay_na | \n",
- " saleDayofweek_na | \n",
- " saleDayofyear_na | \n",
- " saleElapsed_na | \n",
+ " saleIs_year_start | \n",
+ " saleElapsed | \n",
+ " auctioneerID_na | \n",
+ " MachineHoursCurrentMeter_na | \n",
" \n",
" \n",
" \n",
@@ -1209,10 +1209,10 @@
" 1139246 | \n",
" 11.097410 | \n",
" 999089 | \n",
- " 3157 | \n",
+ " 46 | \n",
" ... | \n",
" 1 | \n",
- " 1 | \n",
+ " 2647 | \n",
" 1 | \n",
" 1 | \n",
" \n",
@@ -1221,10 +1221,10 @@
" 1139248 | \n",
" 10.950807 | \n",
" 117657 | \n",
- " 77 | \n",
+ " 13 | \n",
" ... | \n",
" 1 | \n",
- " 1 | \n",
+ " 2148 | \n",
" 1 | \n",
" 1 | \n",
" \n",
@@ -1233,33 +1233,33 @@
" 1139249 | \n",
" 9.210340 | \n",
" 434808 | \n",
- " 7009 | \n",
+ " 9 | \n",
" ... | \n",
" 1 | \n",
- " 1 | \n",
+ " 2131 | \n",
" 1 | \n",
" 1 | \n",
" \n",
" \n",
"\n",
- "3 rows × 79 columns
\n",
+ "3 rows × 67 columns
\n",
""
],
"text/plain": [
- " SalesID SalePrice MachineID ModelID ... saleDay_na saleDayofweek_na \\\n",
- "0 1139246 11.097410 999089 3157 ... 1 1 \n",
- "1 1139248 10.950807 117657 77 ... 1 1 \n",
- "2 1139249 9.210340 434808 7009 ... 1 1 \n",
+ " SalesID SalePrice MachineID saleWeek ... saleIs_year_start \\\n",
+ "0 1139246 11.097410 999089 46 ... 1 \n",
+ "1 1139248 10.950807 117657 13 ... 1 \n",
+ "2 1139249 9.210340 434808 9 ... 1 \n",
"\n",
- " saleDayofyear_na saleElapsed_na \n",
- "0 1 1 \n",
- "1 1 1 \n",
- "2 1 1 \n",
+ " saleElapsed auctioneerID_na MachineHoursCurrentMeter_na \n",
+ "0 2647 1 1 \n",
+ "1 2148 1 1 \n",
+ "2 2131 1 1 \n",
"\n",
- "[3 rows x 79 columns]"
+ "[3 rows x 67 columns]"
]
},
- "execution_count": null,
+ "execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
@@ -1271,7 +1271,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 26,
"metadata": {},
"outputs": [
{
@@ -1334,7 +1334,7 @@
"2 32 3 0 6"
]
},
- "execution_count": null,
+ "execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
@@ -1353,16 +1353,16 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "(#7) ['#na#','Large','Large / Medium','Medium','Small','Mini','Compact']"
+ "['#na#', 'Large', 'Large / Medium', 'Medium', 'Small', 'Mini', 'Compact']"
]
},
- "execution_count": null,
+ "execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
@@ -1380,7 +1380,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
@@ -1421,7 +1421,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
@@ -1431,7 +1431,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
@@ -1448,7 +1448,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
@@ -1465,7 +1465,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 40,
"metadata": {},
"outputs": [
{
@@ -1474,125 +1474,125 @@
"\n",
"\n",
- "\n",
"\n",
- "