First batch changes

# Data Loading Examples

The examples in this directory highlight a number of ways to

load datasets into DeepChem for downstream analysis.

load datasets into DeepChem for downstream analysis: 

- `pandas_csv.py` shows how to directly load a dataset from a CSV file without using a `DataLoader`. 

- `sdf_load.py` shows how to load a dataset from a sdf file using `SDFLoader`. 

# directly.

import pandas as pd

import deepchem as dc

from rdkit import Chem

df = pd.read_csv("example.csv")

print("Original data loaded as DataFrame:")

print(df)

featurizer = dc.feat.CircularFingerprint(size=16)

features = featurizer.featurize(df["smiles"])

dataset = dc.data.NumpyDataset(X=features, y=df["log-solubility"], ids=df["Compound ID"])

mols = [Chem.MolFromSmiles(smiles) for smiles in df["smiles"]]

features = featurizer.featurize(mols)

dataset = dc.data.NumpyDataset(

    X=features, y=df["log-solubility"], ids=df["Compound ID"])

print("Data converted into DeepChem Dataset")

print(dataset)

# This example shows how to load data from a SDF file into DeepChem. The data in this SDF file is stored in field "LogP(RRCK)"

import deepchem as dc

featurizer = dc.feat.CircularFingerprint(size=16)

loader = dc.data.SDFLoader(["LogP(RRCK)"], featurizer=featurizer, sanitize=True)

dataset = loader.featurize("membrane_permeability.sdf")

import numpy as np

import deepchem as dc

mols = ['C1=CC2=C(C=C1)C1=CC=CC=C21', 'O=C1C=CC(=O)C2=C1OC=CO2', 'C1=C[N]C=C1', 'C1=CC=CC=C[C+]1', 'C1=[C]NC=C1', 'N[C@@H](C)C(=O)O', 'N[C@H](C)C(=O)O', 'CC', 'O=C=O', 'C#N', 'CCN(CC)CC', 'CC(=O)O', 'C1CCCCC1', 'c1ccccc1']

mols = [

    'C1=CC2=C(C=C1)C1=CC=CC=C21', 'O=C1C=CC(=O)C2=C1OC=CO2', 'C1=C[N]C=C1',

    'C1=CC=CC=C[C+]1', 'C1=[C]NC=C1', 'N[C@@H](C)C(=O)O', 'N[C@H](C)C(=O)O',

    'CC', 'O=C=O', 'C#N', 'CCN(CC)CC', 'CC(=O)O', 'C1CCCCC1', 'c1ccccc1'

]

print("Original set of molecules")

print(mols)

splitter = dc.splits.ScaffoldSplitter(seed=123)

train, valid, test = splitter.train_valid_test_split(mols)

splitter = dc.splits.ScaffoldSplitter()

# TODO: This should be swapped for simpler splitter API once that's merged in.

dataset = dc.data.NumpyDataset(X=np.array(mols), ids=mols)

train, valid, test = splitter.train_valid_test_split(dataset)

# The return values are dc.data.Dataset objects so we need to extract

# the ids

print("Training set")

print(valid)

print("Test set")

print(test)