Handling merge (866b5ebf) · Commits · 钟慕尧 / deepchem

.travis.yml

+6 −1

Original line number	Diff line number	Diff line
		language: python
		python:
		- '2.7'
		- '3.5'
		sudo: required
		dist: trusty
		install:
		- wget http://repo.continuum.io/archive/Anaconda2-2.4.1-Linux-x86_64.sh -O anaconda.sh;
		- if [[ "$TRAVIS_PYTHON_VERSION" == "2.7" ]]; then
		wget https://repo.continuum.io/archive/Anaconda2-4.2.0-Linux-x86_64.sh -O anaconda.sh;
		else
		wget https://repo.continuum.io/archive/Anaconda3-4.2.0-Linux-x86_64.sh -O anaconda.sh;
		fi
		- bash anaconda.sh -b -p $HOME/anaconda
		- export PATH="$HOME/anaconda/bin:$PATH"
		- hash -r

README.md

+15 −3

Original line number	Diff line number	Diff line
		@@ -22,10 +22,10 @@ Requirements
		Linux (64-bit) Installation from Source
		---------------------------------------

		```deepchem``` currently requires Python 2.7, and is not supported on any platforms except 64 bit linux. Please make sure you follow the directions below precisely. While you may already have system versions of some of these packages, there is no guarantee that `deepchem` will work with alternate versions than those specified below.
		```deepchem``` currently supports both Python 2.7 and Python 3.5, but is not supported on any OS'es except 64 bit linux. Please make sure you follow the directions below precisely. While you may already have system versions of some of these packages, there is no guarantee that `deepchem` will work with alternate versions than those specified below.

		1. Download the 64-bit Python 2.7 or Python 3.5 versions of Anaconda for linux [here](https://www.continuum.io/downloads#_unix).

		1. Anaconda 2.7
		Download the 64-bit Python 2.7 version of Anaconda for linux [here](https://www.continuum.io/downloads#_unix).
		Follow the [installation instructions](http://docs.continuum.io/anaconda/install#linux-install)

		2. `openbabel`
		@@ -138,6 +138,18 @@ Frequently Asked Questions
		conda install nomkl numpy scipy scikit-learn numexpr
		conda remove mkl mkl-service
		```
		2. Question: The test suite is core-dumping for me. What's up?
		```
		[rbharath]$ nosetests -v deepchem --nologcapture
		Illegal instruction (core dumped)
		```

		Answer: This is often due to `openbabel` issues on older linux systems. Open `ipython` and run the following
		```
		In [1]: import openbabel as ob
		```
		If you see a core-dump, then it's a sign there's an issue with your `openbabel` install. Try reinstalling `openbabel` from source for your machine.


		Getting Started
		---------------

deepchem/datasets/init.py

+297 −227

File changed.

Preview size limit exceeded, changes collapsed.

deepchem/datasets/muv_datasets.py

+5 −5

Original line number	Diff line number	Diff line
		@@ -9,7 +9,7 @@ import os
		import numpy as np
		import shutil
		from deepchem.utils.save import load_from_disk
		from deepchem.datasets import Dataset
		from deepchem.datasets import DiskDataset
		from deepchem.featurizers.featurize import DataLoader
		from deepchem.featurizers.fingerprints import CircularFingerprint
		from deepchem.transformers import BalancingTransformer
		@@ -59,7 +59,7 @@ def load_muv(base_dir, reload=True, frac_train=.8):
		dataset = loader.featurize(dataset_file, data_dir)
		regen = True
		else:
		dataset = Dataset(data_dir, reload=True)
		dataset = DiskDataset(data_dir, reload=True)

		# Initialize transformers
		transformers = [
		@@ -69,7 +69,7 @@ def load_muv(base_dir, reload=True, frac_train=.8):
		for transformer in transformers:
		transformer.transform(dataset)

		X, y, w, ids = dataset.to_numpy()
		X, y, w, ids = (dataset.X, dataset.y, dataset.w, dataset.ids)
		num_tasks = 17
		num_train = frac_train * len(dataset)
		MUV_tasks = MUV_tasks[:num_tasks]
		@@ -80,9 +80,9 @@ def load_muv(base_dir, reload=True, frac_train=.8):
		w_train, w_valid = w[:num_train, :num_tasks], w[num_train:, :num_tasks]
		ids_train, ids_valid = ids[:num_train], ids[num_train:]

		train_dataset = Dataset.from_numpy(train_dir, X_train, y_train,
		train_dataset = DiskDataset.from_numpy(train_dir, X_train, y_train,
		w_train, ids_train, MUV_tasks)
		valid_dataset = Dataset.from_numpy(valid_dir, X_valid, y_valid,
		valid_dataset = DiskDataset.from_numpy(valid_dir, X_valid, y_valid,
		w_valid, ids_valid, MUV_tasks)

		return MUV_tasks, (train_dataset, valid_dataset), transformers

deepchem/datasets/pcba_datasets.py

+5 −5

Original line number	Diff line number	Diff line
		@@ -9,7 +9,7 @@ import os
		import numpy as np
		import shutil
		from deepchem.utils.save import load_from_disk
		from deepchem.datasets import Dataset
		from deepchem.datasets import DiskDataset
		from deepchem.featurizers.featurize import DataLoader
		from deepchem.featurizers.fingerprints import CircularFingerprint
		from deepchem.transformers import BalancingTransformer
		@@ -80,7 +80,7 @@ def load_pcba(base_dir, reload=True, frac_train=.8):
		dataset = loader.featurize(dataset_file, data_dir)
		regen = True
		else:
		dataset = Dataset(data_dir, reload=True)
		dataset = DiskDataset(data_dir, reload=True)

		# Initialize transformers
		transformers = [
		@@ -93,7 +93,7 @@ def load_pcba(base_dir, reload=True, frac_train=.8):

		print("About to perform train/valid/test split.")
		num_train = frac_train * len(dataset)
		X, y, w, ids = dataset.to_numpy()
		X, y, w, ids = (dataset.X, dataset.y, dataset.w, dataset.ids)
		num_tasks = 120
		PCBA_tasks = PCBA_tasks[:num_tasks]
		print("Using following tasks")
		@@ -103,9 +103,9 @@ def load_pcba(base_dir, reload=True, frac_train=.8):
		w_train, w_valid = w[:num_train, :num_tasks], w[num_train:, :num_tasks]
		ids_train, ids_valid = ids[:num_train], ids[num_train:]

		train_dataset = Dataset.from_numpy(train_dir, X_train, y_train,
		train_dataset = DiskDataset.from_numpy(train_dir, X_train, y_train,
		w_train, ids_train, PCBA_tasks)
		valid_dataset = Dataset.from_numpy(valid_dir, X_valid, y_valid,
		valid_dataset = DiskDataset.from_numpy(valid_dir, X_valid, y_valid,
		w_valid, ids_valid, PCBA_tasks)

Admin message