[1] Official\n- Atomic Distance Benchmark\n8000+ views, 110+ upvotes
\n\n[2] All in one\n- Molecular Properties EDA and models\n32000+ views, 580+ upvotes\n- Keras Neural Net for CHAMPS\n13000+ views, 240+ upvotes\n- EachType\n6500+ views, 190+ upvotes\n- Giba R + data.table + Simple Features -1.012 LB\n8700+ views, 180+ upvotes\n- Exploring Molecular Properties Data\n6000+ views, 120+ upvotes\n- Validation, feature selection, interpretation etc\n4600+ views, 120+ upvotes\n- EDA and Graph NN baseline modeling\n2300+ views, 50+ upvotes\n- EDA, Features, Models, Starter code in R\n1100+ views, 40+ upvotes
\n\n[3] EDA\n- Simple EDA - Lightgbm autotuning w/Hyperopt\n7000+ views, 170+ upvotes\n- Molecules EDA\n2800+ views, 50+ upvotes\n- EDA for Additional Data: Are They Useful?\n1800+ views, 50+ upvotes\n- CHAMPS Competition : Chemistry Background and EDA\n1300+ views, 30+ upvotes
\n\n[4] Feature engineering\n- Brute force feature engineering\n17000+ views, 340+ upvotes\n- Using meta-features to improve model\n12000+ views, 240+ upvotes\n- Distance - is all you need. LB -1.481\n4200+ views, 170+ upvotes\n- Dataset with number of bonds between atoms\n4600+ views, 130+ upvotes\n- Permutation importance\n2800+ views, 100+ upvotes
\n\n[5] Modelling\n- Predicting Mulliken Charges With ACSF Descriptors\n4500+ views, 160+ upvotes\n- 1. MPNN\n7700+ views, 150+ upvotes
\n\n[6] Library\n- SchNet Starter Kit\n2200+ views, 110+ upvotes\n- V7 Estimation of Mulliken Charges with Open Babel\n3400+ views, 100+ upvotes\n- Using RDKit for Atomic Feature and Visualization\n2600+ views, 100+ upvotes
\n\n[7] Efficiency\n- Just speed up calculate distance from Benchmark\n5700+ views, 160+ upvotes\n- Ultra Fast Distance Matrix Computation\n3900+ views, 160+ upvotes\n- Efficient Metric\n3400+ views, 100+ upvotes
\n\n[8] Visualization\n- How To: Easy Visualization of Molecules.\n4800+ views, 230+ upvotes\n- Training set molecule visualization\n2800+ views, 90+ upvotes\n- 3D Visualization of Molecules with Plotly\n2200+ views, 70+ upvotes\n- Molecule Animations\n850+ views, 60+ upvotes\n- Basic Dashboard of visualizations in R\n500+ views, 30+ upvotes
\n\n[9] Trend\n- The Race to Predict Molecular Properties\n4300+ views, 80+ upvotes\n- Competition analysis - CHAMPS\n500+ views, 20+ upvotes
", "messages": [ { "id": "605241", "postDate": "08/22/2019 07:33:24", "content": "[1] Official\n- Atomic Distance Benchmark\n8000+ views, 110+ upvotes
\n\n[2] All in one\n- Molecular Properties EDA and models\n32000+ views, 580+ upvotes\n- Keras Neural Net for CHAMPS\n13000+ views, 240+ upvotes\n- EachType\n6500+ views, 190+ upvotes\n- Giba R + data.table + Simple Features -1.012 LB\n8700+ views, 180+ upvotes\n- Exploring Molecular Properties Data\n6000+ views, 120+ upvotes\n- Validation, feature selection, interpretation etc\n4600+ views, 120+ upvotes\n- EDA and Graph NN baseline modeling\n2300+ views, 50+ upvotes\n- EDA, Features, Models, Starter code in R\n1100+ views, 40+ upvotes
\n\n[3] EDA\n- Simple EDA - Lightgbm autotuning w/Hyperopt\n7000+ views, 170+ upvotes\n- Molecules EDA\n2800+ views, 50+ upvotes\n- EDA for Additional Data: Are They Useful?\n1800+ views, 50+ upvotes\n- CHAMPS Competition : Chemistry Background and EDA\n1300+ views, 30+ upvotes
\n\n[4] Feature engineering\n- Brute force feature engineering\n17000+ views, 340+ upvotes\n- Using meta-features to improve model\n12000+ views, 240+ upvotes\n- Distance - is all you need. LB -1.481\n4200+ views, 170+ upvotes\n- Dataset with number of bonds between atoms\n4600+ views, 130+ upvotes\n- Permutation importance\n2800+ views, 100+ upvotes
\n\n[5] Modelling\n- Predicting Mulliken Charges With ACSF Descriptors\n4500+ views, 160+ upvotes\n- 1. MPNN\n7700+ views, 150+ upvotes
\n\n[6] Library\n- SchNet Starter Kit\n2200+ views, 110+ upvotes\n- V7 Estimation of Mulliken Charges with Open Babel\n3400+ views, 100+ upvotes\n- Using RDKit for Atomic Feature and Visualization\n2600+ views, 100+ upvotes
\n\n[7] Efficiency\n- Just speed up calculate distance from Benchmark\n5700+ views, 160+ upvotes\n- Ultra Fast Distance Matrix Computation\n3900+ views, 160+ upvotes\n- Efficient Metric\n3400+ views, 100+ upvotes
\n\n[8] Visualization\n- How To: Easy Visualization of Molecules.\n4800+ views, 230+ upvotes\n- Training set molecule visualization\n2800+ views, 90+ upvotes\n- 3D Visualization of Molecules with Plotly\n2200+ views, 70+ upvotes\n- Molecule Animations\n850+ views, 60+ upvotes\n- Basic Dashboard of visualizations in R\n500+ views, 30+ upvotes
\n\n[9] Trend\n- The Race to Predict Molecular Properties\n4300+ views, 80+ upvotes\n- Competition analysis - CHAMPS\n500+ views, 20+ upvotes
", "rawMarkdown": "[1] Official\n- [Atomic Distance Benchmark](https://www.kaggle.com/inversion/atomic-distance-benchmark/)\n8000+ views, 110+ upvotes\n\n[2] All in one\n- [Molecular Properties EDA and models](https://www.kaggle.com/artgor/molecular-properties-eda-and-models)\n32000+ views, 580+ upvotes\n- [Keras Neural Net for CHAMPS](https://www.kaggle.com/todnewman/keras-neural-net-for-champs)\n13000+ views, 240+ upvotes\n- [EachType](https://www.kaggle.com/adrianoavelar/eachtype#8.-References)\n6500+ views, 190+ upvotes\n- [Giba R + data.table + Simple Features -1.012 LB](https://www.kaggle.com/titericz/giba-r-data-table-simple-features-1-17-lb)\n8700+ views, 180+ upvotes\n- [Exploring Molecular Properties Data](https://www.kaggle.com/robikscube/exploring-molecular-properties-data#The-Data)\n6000+ views, 120+ upvotes\n- [Validation, feature selection, interpretation etc](https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc#Functions-used-in-this-kernel)\n4600+ views, 120+ upvotes\n- [EDA and Graph NN baseline modeling](https://www.kaggle.com/corochann/eda-and-graph-nn-baseline-modeling)\n2300+ views, 50+ upvotes\n- [EDA, Features, Models, Starter code in R](https://www.kaggle.com/rohanrao/eda-features-models-starter-code-in-r)\n1100+ views, 40+ upvotes\n\n[3] EDA\n- [Simple EDA - Lightgbm autotuning w/Hyperopt](https://www.kaggle.com/kabure/simple-eda-lightgbm-autotuning-w-hyperopt)\n7000+ views, 170+ upvotes\n- [Molecules EDA](https://www.kaggle.com/allunia/molecules-eda)\n2800+ views, 50+ upvotes\n- [EDA for Additional Data: Are They Useful?](https://www.kaggle.com/code1110/eda-for-additional-data-are-they-useful)\n1800+ views, 50+ upvotes\n- [CHAMPS Competition : Chemistry Background and EDA](https://www.kaggle.com/tarunpaparaju/champs-competition-chemistry-background-and-eda)\n1300+ views, 30+ upvotes\n\n\n[4] Feature engineering\n- [Brute force feature engineering](https://www.kaggle.com/artgor/brute-force-feature-engineering)\n17000+ views, 340+ upvotes\n- [Using meta-features to improve model](https://www.kaggle.com/artgor/using-meta-features-to-improve-model)\n12000+ views, 240+ upvotes\n- [Distance - is all you need. LB -1.481](https://www.kaggle.com/criskiev/distance-is-all-you-need-lb-1-481#Build-Distance-Dataset)\n4200+ views, 170+ upvotes\n- [Dataset with number of bonds between atoms](https://www.kaggle.com/asauve/dataset-with-number-of-bonds-between-atoms)\n4600+ views, 130+ upvotes\n- [Permutation importance](https://www.kaggle.com/speedwagon/permutation-importance)\n2800+ views, 100+ upvotes\n\n[5] Modelling\n- [Predicting Mulliken Charges With ACSF Descriptors](https://www.kaggle.com/borisdee/predicting-mulliken-charges-with-acsf-descriptors)\n4500+ views, 160+ upvotes\n- [1. MPNN](https://www.kaggle.com/fnands/1-mpnn)\n7700+ views, 150+ upvotes\n\n[6] Library\n- [SchNet Starter Kit](https://www.kaggle.com/toshik/schnet-starter-kit#Preprocessing)\n2200+ views, 110+ upvotes\n- [V7 Estimation of Mulliken Charges with Open Babel](https://www.kaggle.com/asauve/v7-estimation-of-mulliken-charges-with-open-babel#Synopsis)\n3400+ views, 100+ upvotes\n- [Using RDKit for Atomic Feature and Visualization](https://www.kaggle.com/sunhwan/using-rdkit-for-atomic-feature-and-visualization)\n2600+ views, 100+ upvotes\n\n[7] Efficiency\n- [Just speed up calculate distance from Benchmark](https://www.kaggle.com/seriousran/just-speed-up-calculate-distance-from-benchmark)\n5700+ views, 160+ upvotes\n- [Ultra Fast Distance Matrix Computation](https://www.kaggle.com/cpmpml/ultra-fast-distance-matrix-computation)\n3900+ views, 160+ upvotes\n- [Efficient Metric](https://www.kaggle.com/uberkinder/efficient-metric)\n3400+ views, 100+ upvotes\n\n[8] Visualization\n- [How To: Easy Visualization of Molecules.](https://www.kaggle.com/borisdee/how-to-easy-visualization-of-molecules)\n4800+ views, 230+ upvotes\n- [Training set molecule visualization](https://www.kaggle.com/asauve/training-set-molecule-visualization)\n2800+ views, 90+ upvotes\n- [3D Visualization of Molecules with Plotly](https://www.kaggle.com/mykolazotko/3d-visualization-of-molecules-with-plotly)\n2200+ views, 70+ upvotes\n- [Molecule Animations](https://www.kaggle.com/cdeotte/molecule-animations)\n850+ views, 60+ upvotes\n- [Basic Dashboard of visualizations in R](https://www.kaggle.com/rohanrao/basic-dashboard-of-visualizations-in-r)\n500+ views, 30+ upvotes\n\n[9] Trend\n- [The Race to Predict Molecular Properties](https://www.kaggle.com/robikscube/the-race-to-predict-molecular-properties)\n4300+ views, 80+ upvotes\n- [Competition analysis - CHAMPS](https://www.kaggle.com/somnambwl/competition-analysis-champs)\n500+ views, 20+ upvotes", "votes": null }, { "id": "605242", "postDate": "08/22/2019 07:34:59", "content": "If you want to add or modify something, just let me know.
", "rawMarkdown": "If you want to add or modify something, just let me know.", "votes": null }, { "id": "606289", "postDate": "08/23/2019 11:48:12", "content": "Very Informative..... Thanks..!! @kimjihoo
", "rawMarkdown": "Very Informative..... Thanks..!! @kimjihoo", "votes": null } ], "comments": [ { "id": 605242, "author_name": "kimjihoo", "author_url": "", "post_date": "08/22/2019 07:34:59", "content": "If you want to add or modify something, just let me know.
", "votes": null, "replies": [] }, { "id": 606289, "author_name": "veeralakrishna", "author_url": "", "post_date": "08/23/2019 11:48:12", "content": "Very Informative..... Thanks..!! @kimjihoo
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "605241": "[1] Official\n- [Atomic Distance Benchmark](https://www.kaggle.com/inversion/atomic-distance-benchmark/)\n8000+ views, 110+ upvotes\n\n[2] All in one\n- [Molecular Properties EDA and models](https://www.kaggle.com/artgor/molecular-properties-eda-and-models)\n32000+ views, 580+ upvotes\n- [Keras Neural Net for CHAMPS](https://www.kaggle.com/todnewman/keras-neural-net-for-champs)\n13000+ views, 240+ upvotes\n- [EachType](https://www.kaggle.com/adrianoavelar/eachtype#8.-References)\n6500+ views, 190+ upvotes\n- [Giba R + data.table + Simple Features -1.012 LB](https://www.kaggle.com/titericz/giba-r-data-table-simple-features-1-17-lb)\n8700+ views, 180+ upvotes\n- [Exploring Molecular Properties Data](https://www.kaggle.com/robikscube/exploring-molecular-properties-data#The-Data)\n6000+ views, 120+ upvotes\n- [Validation, feature selection, interpretation etc](https://www.kaggle.com/artgor/validation-feature-selection-interpretation-etc#Functions-used-in-this-kernel)\n4600+ views, 120+ upvotes\n- [EDA and Graph NN baseline modeling](https://www.kaggle.com/corochann/eda-and-graph-nn-baseline-modeling)\n2300+ views, 50+ upvotes\n- [EDA, Features, Models, Starter code in R](https://www.kaggle.com/rohanrao/eda-features-models-starter-code-in-r)\n1100+ views, 40+ upvotes\n\n[3] EDA\n- [Simple EDA - Lightgbm autotuning w/Hyperopt](https://www.kaggle.com/kabure/simple-eda-lightgbm-autotuning-w-hyperopt)\n7000+ views, 170+ upvotes\n- [Molecules EDA](https://www.kaggle.com/allunia/molecules-eda)\n2800+ views, 50+ upvotes\n- [EDA for Additional Data: Are They Useful?](https://www.kaggle.com/code1110/eda-for-additional-data-are-they-useful)\n1800+ views, 50+ upvotes\n- [CHAMPS Competition : Chemistry Background and EDA](https://www.kaggle.com/tarunpaparaju/champs-competition-chemistry-background-and-eda)\n1300+ views, 30+ upvotes\n\n\n[4] Feature engineering\n- [Brute force feature engineering](https://www.kaggle.com/artgor/brute-force-feature-engineering)\n17000+ views, 340+ upvotes\n- [Using meta-features to improve model](https://www.kaggle.com/artgor/using-meta-features-to-improve-model)\n12000+ views, 240+ upvotes\n- [Distance - is all you need. LB -1.481](https://www.kaggle.com/criskiev/distance-is-all-you-need-lb-1-481#Build-Distance-Dataset)\n4200+ views, 170+ upvotes\n- [Dataset with number of bonds between atoms](https://www.kaggle.com/asauve/dataset-with-number-of-bonds-between-atoms)\n4600+ views, 130+ upvotes\n- [Permutation importance](https://www.kaggle.com/speedwagon/permutation-importance)\n2800+ views, 100+ upvotes\n\n[5] Modelling\n- [Predicting Mulliken Charges With ACSF Descriptors](https://www.kaggle.com/borisdee/predicting-mulliken-charges-with-acsf-descriptors)\n4500+ views, 160+ upvotes\n- [1. MPNN](https://www.kaggle.com/fnands/1-mpnn)\n7700+ views, 150+ upvotes\n\n[6] Library\n- [SchNet Starter Kit](https://www.kaggle.com/toshik/schnet-starter-kit#Preprocessing)\n2200+ views, 110+ upvotes\n- [V7 Estimation of Mulliken Charges with Open Babel](https://www.kaggle.com/asauve/v7-estimation-of-mulliken-charges-with-open-babel#Synopsis)\n3400+ views, 100+ upvotes\n- [Using RDKit for Atomic Feature and Visualization](https://www.kaggle.com/sunhwan/using-rdkit-for-atomic-feature-and-visualization)\n2600+ views, 100+ upvotes\n\n[7] Efficiency\n- [Just speed up calculate distance from Benchmark](https://www.kaggle.com/seriousran/just-speed-up-calculate-distance-from-benchmark)\n5700+ views, 160+ upvotes\n- [Ultra Fast Distance Matrix Computation](https://www.kaggle.com/cpmpml/ultra-fast-distance-matrix-computation)\n3900+ views, 160+ upvotes\n- [Efficient Metric](https://www.kaggle.com/uberkinder/efficient-metric)\n3400+ views, 100+ upvotes\n\n[8] Visualization\n- [How To: Easy Visualization of Molecules.](https://www.kaggle.com/borisdee/how-to-easy-visualization-of-molecules)\n4800+ views, 230+ upvotes\n- [Training set molecule visualization](https://www.kaggle.com/asauve/training-set-molecule-visualization)\n2800+ views, 90+ upvotes\n- [3D Visualization of Molecules with Plotly](https://www.kaggle.com/mykolazotko/3d-visualization-of-molecules-with-plotly)\n2200+ views, 70+ upvotes\n- [Molecule Animations](https://www.kaggle.com/cdeotte/molecule-animations)\n850+ views, 60+ upvotes\n- [Basic Dashboard of visualizations in R](https://www.kaggle.com/rohanrao/basic-dashboard-of-visualizations-in-r)\n500+ views, 30+ upvotes\n\n[9] Trend\n- [The Race to Predict Molecular Properties](https://www.kaggle.com/robikscube/the-race-to-predict-molecular-properties)\n4300+ views, 80+ upvotes\n- [Competition analysis - CHAMPS](https://www.kaggle.com/somnambwl/competition-analysis-champs)\n500+ views, 20+ upvotes", "605242": "If you want to add or modify something, just let me know.", "606289": "Very Informative..... Thanks..!! @kimjihoo" }, "source": "meta" }