Flattened jupyter notebooks containing the analysis workflow in the manuscript A quantitative model for the prediction of sooting tendency from molecular structure.
Full repository (with data files) is available at pstjohn/ysi_qsar_energy_fuels
Last active
September 5, 2019 22:53
-
-
Save pstjohn/b7e2f05136bf8bfd22f68f375437452d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: ysi | |
| channels: | |
| - https://conda.anaconda.org/rdkit | |
| dependencies: | |
| - python=3.5 | |
| - jupyter | |
| - pandas | |
| - seaborn | |
| - rdkit | |
| - jinja2 | |
| - pip: | |
| - https://github.com/pstjohn/scikit-learn/archive/pstjohn-changes.zip | |
| - pubchempy | |
| - keras==0.3.3 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "code", | |
| "execution_count": 1, | |
| "metadata": { | |
| "collapsed": false | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "import numpy as np\n", | |
| "np.random.seed(0)\n", | |
| "import pandas as pd\n", | |
| "\n", | |
| "import matplotlib.pyplot as plt\n", | |
| "import seaborn as sns\n", | |
| "sns.set_style('darkgrid')\n", | |
| "sns.set_context('talk', font_scale=1.5)\n", | |
| "sns.set(color_codes=True)\n", | |
| "\n", | |
| "import matplotlib.gridspec as gridspec\n", | |
| "\n", | |
| "%matplotlib inline" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 2, | |
| "metadata": { | |
| "collapsed": false | |
| }, | |
| "outputs": [ | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "Using Theano backend.\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "from ysi_utils.models.setup_model import model\n", | |
| "\n", | |
| "from ysi_utils.data import low\n", | |
| "from ysi_utils.descriptors import dragon\n", | |
| "from ysi_utils.validation import y_train as y\n", | |
| "from ysi_utils.validation import y_test\n", | |
| "\n", | |
| "X = dragon.loc[y.index]\n", | |
| "X_test = dragon.loc[y_test.index]" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 3, | |
| "metadata": { | |
| "collapsed": true | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "from sklearn.ensemble import BaggingRegressor\n", | |
| "from sklearn.metrics import median_absolute_error" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "*This next step takes a considerable amount of computing time, since the model is refit 25 times*" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 4, | |
| "metadata": { | |
| "collapsed": false | |
| }, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "BaggingRegressor(base_estimator=Pipeline(steps=[('imputer', Imputer(axis=0, copy=True, missing_values='NaN', strategy='mean', verbose=0)), ('filter', VarianceThreshold(threshold=0.0)), ('scaler', MaxAbsScaler(copy=True)), ('feature_extraction', RFE(estimator=SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, gamma='auto',\n", | |
| " kerne...step=10, verbose=0)), ('ffann', <keras.wrappers.scikit_learn.KerasRegressor object at 0x111467588>)]),\n", | |
| " bootstrap=False, bootstrap_features=False, max_features=1.0,\n", | |
| " max_samples=0.9, n_estimators=25, n_jobs=1, oob_score=False,\n", | |
| " random_state=0, verbose=False, warm_start=False)" | |
| ] | |
| }, | |
| "execution_count": 4, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "bagging_model = BaggingRegressor(base_estimator=model, random_state=0, verbose=False,\n", | |
| " max_samples=.9, bootstrap=False, n_estimators=25)\n", | |
| "bagging_model.fit(X.values, y.YSI.values)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 5, | |
| "metadata": { | |
| "collapsed": true | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "import keras" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 6, | |
| "metadata": { | |
| "collapsed": false | |
| }, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "'0.3.3'" | |
| ] | |
| }, | |
| "execution_count": 6, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "keras.__version__" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 7, | |
| "metadata": { | |
| "collapsed": false | |
| }, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "['../ysi_utils/models/bagging_model.pkl.large']" | |
| ] | |
| }, | |
| "execution_count": 7, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "import sys\n", | |
| "# This is required to prevent errors on pickling.\n", | |
| "sys.setrecursionlimit(10000)\n", | |
| "\n", | |
| "from sklearn.externals import joblib\n", | |
| "joblib.dump(bagging_model, '../ysi_utils/models/bagging_model.pkl.large', compress=9)" | |
| ] | |
| } | |
| ], | |
| "metadata": { | |
| "anaconda-cloud": {}, | |
| "kernelspec": { | |
| "display_name": "Python [conda env:ysi]", | |
| "language": "python", | |
| "name": "conda-env-ysi-py" | |
| }, | |
| "language_info": { | |
| "codemirror_mode": { | |
| "name": "ipython", | |
| "version": 3 | |
| }, | |
| "file_extension": ".py", | |
| "mimetype": "text/x-python", | |
| "name": "python", | |
| "nbconvert_exporter": "python", | |
| "pygments_lexer": "ipython3", | |
| "version": "3.5.2" | |
| } | |
| }, | |
| "nbformat": 4, | |
| "nbformat_minor": 0 | |
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| np.random.seed(0) | |
| from keras.models import Sequential | |
| from keras.layers.core import Dense, Dropout, Activation | |
| from keras.wrappers.scikit_learn import KerasRegressor | |
| from sklearn.pipeline import Pipeline | |
| from sklearn.preprocessing import (StandardScaler, Normalizer, RobustScaler, | |
| MaxAbsScaler, Imputer) | |
| from sklearn.decomposition import PCA | |
| from sklearn.feature_selection import VarianceThreshold, RFE, SelectKBest, f_regression | |
| from sklearn import svm | |
| from ysi_utils.descriptors import dragon | |
| from ysi_utils.validation import y_train as y | |
| from ysi_utils.validation import y_test | |
| X = dragon.loc[y.index] | |
| X_test = dragon.loc[y_test.index] | |
| # These are the optimal parameters as selected by the hyperopt fitting routine. | |
| params = \ | |
| {'activation': 'relu', | |
| 'batch_size': 39, | |
| 'dropout1': 0.36632971139053216, | |
| 'dropout2': 0.030115015871571206, | |
| 'feature_extractor': {'n_features_to_select': 390, 'step': 10, 'type': 'RFE'}, | |
| 'nb_epochs': 100, | |
| 'num_layers': {'dropout3': 0.31435729897990794, | |
| 'layers': 'three', | |
| 'units3': 161}, | |
| 'optimizer': 'adam', | |
| 'preprocessor': 'MaxAbsScaler', | |
| 'units1': 140, | |
| 'units2': 140} | |
| def get_input_size(params): | |
| if 'n_components' in params['feature_extractor']: | |
| return params['feature_extractor']['n_components'] | |
| elif 'k' in params['feature_extractor']: | |
| return params['feature_extractor']['k'] | |
| elif 'n_features_to_select' in params['feature_extractor']: | |
| return params['feature_extractor']['n_features_to_select'] | |
| def build_model(params=params): | |
| model = Sequential() | |
| model.add(Dense(output_dim=params['units1'], | |
| input_dim=get_input_size(params))) | |
| model.add(Activation(params['activation'])) | |
| model.add(Dropout(params['dropout1'])) | |
| model.add(Dense(output_dim=params['units2'], init="glorot_uniform")) | |
| model.add(Activation(params['activation'])) | |
| model.add(Dropout(params['dropout2'])) | |
| if params['num_layers']['layers']== 'three': | |
| model.add(Dense(output_dim=params['num_layers']['units3'], init="glorot_uniform")) | |
| model.add(Activation(params['activation'])) | |
| model.add(Dropout(params['num_layers']['dropout3'])) | |
| model.add(Dense(output_dim=1)) | |
| model.compile(loss='mae', optimizer=params['optimizer']) | |
| return model | |
| ffann = KerasRegressor(build_fn=build_model, | |
| nb_epoch=params['nb_epochs'], | |
| batch_size=params['batch_size'], | |
| verbose=0) | |
| # Set up preprocessing pipeline | |
| imputer = Imputer() | |
| var_filter = VarianceThreshold() | |
| preprocessor_dict = { | |
| 'StandardScaler' : StandardScaler, | |
| 'MaxAbsScaler' : MaxAbsScaler, | |
| 'Normalizer' : Normalizer, | |
| 'RobustScaler' : RobustScaler, | |
| } | |
| scaler = preprocessor_dict[params['preprocessor']]() | |
| if params['feature_extractor']['type'] == 'pca': | |
| opts = dict(params['feature_extractor']) | |
| del opts['type'] | |
| feature_extraction = PCA(**opts) | |
| elif params['feature_extractor']['type'] == 'RFE': | |
| opts = dict(params['feature_extractor']) | |
| del opts['type'] | |
| svr = svm.SVR(kernel='linear') | |
| feature_extraction = RFE(estimator=svr, **opts) | |
| elif params['feature_extractor']['type'] == 'SelectKBest': | |
| opts = dict(params['feature_extractor']) | |
| del opts['type'] | |
| feature_extraction = SelectKBest(score_func=f_regression, **opts) | |
| model = Pipeline(steps=[ | |
| ('imputer', imputer), | |
| ('filter', var_filter), | |
| ('scaler', scaler), | |
| ('feature_extraction', feature_extraction), | |
| ('ffann', ffann) | |
| ]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment