|
19 | 19 | "You will need to know some very basic SQL syntax to fully understand this notebook." |
20 | 20 | ] |
21 | 21 | }, |
| 22 | + { |
| 23 | + "cell_type": "markdown", |
| 24 | + "metadata": {}, |
| 25 | + "source": [ |
| 26 | + "## Examples" |
| 27 | + ] |
| 28 | + }, |
22 | 29 | { |
23 | 30 | "cell_type": "code", |
24 | 31 | "execution_count": 1, |
|
55 | 62 | "cell_type": "markdown", |
56 | 63 | "metadata": {}, |
57 | 64 | "source": [ |
58 | | - "## Download data" |
| 65 | + "### Download data" |
59 | 66 | ] |
60 | 67 | }, |
61 | 68 | { |
62 | 69 | "cell_type": "markdown", |
63 | 70 | "metadata": {}, |
64 | 71 | "source": [ |
65 | | - "### Training/test data" |
| 72 | + "#### Training/test data" |
66 | 73 | ] |
67 | 74 | }, |
68 | 75 | { |
|
116 | 123 | "cell_type": "markdown", |
117 | 124 | "metadata": {}, |
118 | 125 | "source": [ |
119 | | - "## Get X and y" |
| 126 | + "### Get X and y" |
120 | 127 | ] |
121 | 128 | }, |
122 | 129 | { |
|
620 | 627 | "cell_type": "markdown", |
621 | 628 | "metadata": {}, |
622 | 629 | "source": [ |
623 | | - "## First thing first: Spatiotemporal train test split" |
| 630 | + "### First thing first: Spatiotemporal train test split" |
624 | 631 | ] |
625 | 632 | }, |
626 | 633 | { |
|
642 | 649 | "cell_type": "markdown", |
643 | 650 | "metadata": {}, |
644 | 651 | "source": [ |
645 | | - "## Initiate AdaSTEM hurdle model" |
| 652 | + "### Initiate AdaSTEM hurdle model" |
646 | 653 | ] |
647 | 654 | }, |
648 | 655 | { |
|
701 | 708 | "cell_type": "markdown", |
702 | 709 | "metadata": {}, |
703 | 710 | "source": [ |
704 | | - "## \"Traditional\" fit with pandas object" |
| 711 | + "### \"Traditional\" fit with pandas object" |
705 | 712 | ] |
706 | 713 | }, |
707 | 714 | { |
|
1275 | 1282 | "cell_type": "markdown", |
1276 | 1283 | "metadata": {}, |
1277 | 1284 | "source": [ |
1278 | | - "## Dump data into duckdb database" |
| 1285 | + "### Dump data into duckdb database" |
1279 | 1286 | ] |
1280 | 1287 | }, |
1281 | 1288 | { |
|
2192 | 2199 | "cell_type": "markdown", |
2193 | 2200 | "metadata": {}, |
2194 | 2201 | "source": [ |
2195 | | - "## Using duckdb as input\n" |
| 2202 | + "### Using duckdb as input\n" |
2196 | 2203 | ] |
2197 | 2204 | }, |
2198 | 2205 | { |
|
3344 | 3351 | "cell_type": "markdown", |
3345 | 3352 | "metadata": {}, |
3346 | 3353 | "source": [ |
3347 | | - "## Using parquet as input" |
| 3354 | + "### Using parquet as input" |
3348 | 3355 | ] |
3349 | 3356 | }, |
3350 | 3357 | { |
|
3937 | 3944 | "cell_type": "markdown", |
3938 | 3945 | "metadata": {}, |
3939 | 3946 | "source": [ |
3940 | | - "## Compare the three method: pd.DataFrame, parquet, and duckdb\n", |
| 3947 | + "### Compare the three method: pd.DataFrame, parquet, and duckdb\n", |
3941 | 3948 | "-- Speed, memory use" |
3942 | 3949 | ] |
3943 | 3950 | }, |
|
4076 | 4083 | "cell_type": "markdown", |
4077 | 4084 | "metadata": {}, |
4078 | 4085 | "source": [ |
4079 | | - "# On Small dataset" |
| 4086 | + "## On Small dataset" |
4080 | 4087 | ] |
4081 | 4088 | }, |
4082 | 4089 | { |
|
4090 | 4097 | "cell_type": "markdown", |
4091 | 4098 | "metadata": {}, |
4092 | 4099 | "source": [ |
4093 | | - "## Run test: Training using pd.DataFrame, duckdb, and pandas. Increasing ensemble_fold" |
| 4100 | + "### Run test: Training using pd.DataFrame, duckdb, and pandas. Increasing ensemble_fold" |
4094 | 4101 | ] |
4095 | 4102 | }, |
4096 | 4103 | { |
|
4839 | 4846 | "cell_type": "markdown", |
4840 | 4847 | "metadata": {}, |
4841 | 4848 | "source": [ |
4842 | | - "## Run test: Training using pd.DataFrame, duckdb, and pandas. Increasing n_jobs" |
| 4849 | + "### Run test: Training using pd.DataFrame, duckdb, and pandas. Increasing n_jobs" |
4843 | 4850 | ] |
4844 | 4851 | }, |
4845 | 4852 | { |
|
5376 | 5383 | "cell_type": "markdown", |
5377 | 5384 | "metadata": {}, |
5378 | 5385 | "source": [ |
5379 | | - "# On larger dataset" |
| 5386 | + "## On larger dataset" |
5380 | 5387 | ] |
5381 | 5388 | }, |
5382 | 5389 | { |
|
5497 | 5504 | "cell_type": "markdown", |
5498 | 5505 | "metadata": {}, |
5499 | 5506 | "source": [ |
5500 | | - "## Run test: Training using pd.DataFrame, duckdb, and pandas. Increasing n_jobs" |
| 5507 | + "### Run test: Training using pd.DataFrame, duckdb, and pandas. Increasing n_jobs" |
5501 | 5508 | ] |
5502 | 5509 | }, |
5503 | 5510 | { |
|
0 commit comments