Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Implement sort for data panel and columns #237

Merged
merged 15 commits into from
Jun 23, 2022
Merged

Implement sort for data panel and columns #237

Show file tree
Hide file tree
Changes from 9 commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
50a3a6a
Add function headers for sort
seyuboglu Apr 20, 2022
490dfbd
Add notebook
seyuboglu Apr 20, 2022
2b86273
Initial sort updates
hannahkim24 Apr 27, 2022
58d8fc8
More sort column changes
hannahkim24 Apr 28, 2022
16f4dca
Updates for datapanel sort
hannahkim24 May 19, 2022
0c8d8d4
Initial tests
hannahkim24 Jun 1, 2022
623f3db
Test updates
hannahkim24 Jun 2, 2022
3781c00
testing
hannahkim24 Jun 2, 2022
12405db
Fix issue with misaligned indicies in pandas block
seyuboglu Jun 2, 2022
484397d
testing updates
hannahkim24 Jun 2, 2022
b0858d9
fixed pandas col comparison
hannahkim24 Jun 2, 2022
d3fb051
Merge branch 'feature/sort' of https://github.com/robustness-gym/meer…
hannahkim24 Jun 2, 2022
926c236
Testing sort changes and sort implementation fixes
hannahkim24 Jun 9, 2022
cd80f01
Final test and sort implementation changes
hannahkim24 Jun 9, 2022
ce62892
Address autoformat
hannahkim24 Jun 23, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,3 +146,9 @@ dmypy.json
# Pyre type checker
.pyre/

# Giant file
examples/datasets

# History
.history

6,064 changes: 3,013 additions & 3,051 deletions examples/01-meerkat_intro.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

346 changes: 346 additions & 0 deletions examples/4-20_sort.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,346 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import meerkat as mk\n",
"import os\n",
"import torch\n",
"import numpy as np\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>text (TensorColumn)</th>\n",
" <th>image (PandasSeriesColumn)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>tensor(1)</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>tensor(5)</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>tensor(1)</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>tensor(4)</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>tensor(3)</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>tensor(4)</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>tensor(4)</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"DataPanel(nrows: 7, ncols: 2)"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dp2 = mk.DataPanel({\n",
" 'text': mk.TensorColumn([1,5,1,4,3,4,4]), \n",
" 'image': mk.PandasSeriesColumn([9,4,0,4,0,2,1]), \n",
" \n",
"}) \n",
"\n",
"dp2\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'meerkat.columns.numpy_column.NumpyArrayColumn'>\n",
"<class 'meerkat.columns.numpy_column.NumpyArrayColumn'>\n"
]
},
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>image (NumpyArrayColumn)</th>\n",
" <th>text (NumpyArrayColumn)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>9</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"DataPanel(nrows: 7, ncols: 2)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dp2.sort(by=[\"text\", \"image\"], ascending=True)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>(NumpyArrayColumn)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"NumpyArrayColumn(array([1, 5, 1, 4, 3, 4, 4]))"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dp2[\"text\"]\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"test2 = mk.PandasSeriesColumn([3,2, 1])"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"test2 = mk.DataPanel({\n",
" 'tensor': mk.TensorColumn([3,1,2]), \n",
" 'pandas': mk.PandasSeriesColumn([5,4,6]), \n",
" }) \n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"test1 = test2.sort(by=[\"tensor\"])\n",
"test3 = test2.sort(by=[\"pandas\"])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>tensor (TensorColumn)</th>\n",
" <th>pandas (PandasSeriesColumn)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>tensor(1)</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>tensor(2)</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>tensor(3)</td>\n",
" <td>5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"DataPanel(nrows: 3, ncols: 2)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test1\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
4 changes: 4 additions & 0 deletions meerkat/block/pandas_block.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,10 @@ def _get(
return {
name: data[col._block_index] for name, col in block_ref.columns.items()
}

# All Pandas Columns should have contiguous indices so that we can perform
# comparisons etc.
data = data.reset_index(drop=True)
block = self.__class__(data)

columns = {
Expand Down
Loading