Skip to content

Commit

Permalink
Updated tutorials and regression metrics
Browse files Browse the repository at this point in the history
  • Loading branch information
@aatishpr
aatishpr committed Nov 9, 2021
1 parent d8be220 commit a33f050
Show file tree
Hide file tree
Showing 7 changed files with 293 additions and 127 deletions.
4 changes: 2 additions & 2 deletions chemml/__init__.py
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# __name__ = "chemml"
__version__ = "0.8"
__author__ = ["Mojtaba Haghighatlari ([email protected])", "Johannes Hachmann ([email protected])"]
__version__ = "1.0"
__author__ = ["Aditya Sonpal ([email protected])", "Garuav Vishwakarma ([email protected]) ", "Aatish Pradhan ([email protected])","Mojtaba Haghighatlari ([email protected])", "Johannes Hachmann ([email protected])"]


# import sys
Expand Down
1 change: 1 addition & 0 deletions chemml/models/keras/mlp.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -130,6 +130,7 @@ def save(self, path, filename):
obj_dict['path_to_file'] = path +'/'+ filename+'.h5'
obj_df = pd.DataFrame.from_dict(obj_dict,orient='index')
obj_df.to_csv(path+'/'+filename+'_chemml_model.csv')
print("File saved as "+path+"/"+filename+"_chemml_model.csv")

def load(self, path_to_model):
"""
Expand Down
2 changes: 1 addition & 1 deletion chemml/utils/utilities.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -384,7 +384,7 @@ def regression_metrics(y_true, y_predicted, nfeatures = None):
metrics_dict['AE'] = [list(ae)]
metrics_dict['SE'] = [list(se)]

var = np.mean(np.square(y_predicted - y_mean))
var = np.mean(np.square(y_true - y_mean))

metrics_dict['ME'] = np.mean(e)
# mean absolute error
Expand Down
49 changes: 39 additions & 10 deletions docs/ipython_notebooks/Convo_nets.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,18 @@
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2021-11-09 18:22:23.552207: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
"2021-11-09 18:22:23.552291: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n",
"/mnt/c/Aatish/UB/Mr. Hachmann/master_chemml_wrapper_v2/chemml/chemml/datasets/base.py:87: FutureWarning: In a future version of pandas all arguments of DataFrame.drop except for the argument 'labels' will be keyword-only\n",
" features = df.drop(['smiles', 'density_Kg/m3'],1)\n"
]
}
],
"source": [
"import numpy as np\n",
"from chemml.datasets import load_organic_density\n",
Expand Down Expand Up @@ -62,7 +73,7 @@
"output_type": "stream",
"text": [
"Tensorising molecules in batches of 100 ...\n",
"500/500 [==================================================] - 0s 601us/step\n",
"500/500 [==================================================] - 1s 1ms/step\n",
"Merging batch tensors ... [DONE]\n"
]
}
Expand Down Expand Up @@ -156,6 +167,17 @@
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2021-11-09 18:23:03.337511: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory\n",
"2021-11-09 18:23:03.337613: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)\n",
"2021-11-09 18:23:03.337645: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (Aatish-HP): /proc/driver/nvidia/version does not exist\n",
"2021-11-09 18:23:03.337984: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n",
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
Expand Down Expand Up @@ -262,10 +284,17 @@
"__________________________________________________________________________________________________\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2021-11-09 18:23:04.812435: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)\n"
]
},
{
"data": {
"text/plain": [
"<tensorflow.python.keras.callbacks.History at 0x7fac474e07b8>"
"<keras.callbacks.History at 0x7feda4198be0>"
]
},
"execution_count": 7,
Expand Down Expand Up @@ -312,8 +341,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Mean Absolute Error = 18.407 kg/m^3\n",
"R squared = 0.903\n"
"Mean Absolute Error = 16.518 kg/m^3\n",
"R squared = 0.935\n"
]
}
],
Expand All @@ -322,9 +351,9 @@
"\n",
"y_pred = model.predict([xatoms_test,xbonds_test,xedges_test])\n",
"y_pred = y_scale.inverse_transform(y_pred)\n",
"metrics_dict = regression_metrics(target_test, list(y_pred.reshape(-1,)))\n",
"mae = metrics_dict['MAE']\n",
"r_2 = metrics_dict['r_squared']\n",
"metrics_df = regression_metrics(target_test, list(y_pred.reshape(-1,)))\n",
"mae = metrics_df['MAE'].values[0]\n",
"r_2 = metrics_df['r_squared'].values[0]\n",
"\n",
"print(\"Mean Absolute Error = {} kg/m^3\".format(mae.round(3)))\n",
"print(\"R squared = {}\".format(r_2.round(3)))"
Expand All @@ -333,9 +362,9 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "Python [conda env:chemml_env] *",
"language": "python",
"name": "python3"
"name": "conda-env-chemml_env-py"
},
"language_info": {
"codemirror_mode": {
Expand Down
109 changes: 56 additions & 53 deletions docs/ipython_notebooks/ga_hyper_opt.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,16 @@
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2021-11-09 18:23:58.580965: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
"2021-11-09 18:23:58.581035: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n",
"/mnt/c/Aatish/UB/Mr. Hachmann/master_chemml_wrapper_v2/chemml/chemml/datasets/base.py:87: FutureWarning: In a future version of pandas all arguments of DataFrame.drop except for the argument 'labels' will be keyword-only\n",
" features = df.drop(['smiles', 'density_Kg/m3'],1)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
Expand Down Expand Up @@ -91,7 +101,7 @@
" krr = KernelRidge(alpha=individual[0], kernel=individual[1], degree=individual[2])\n",
" krr.fit(features[:400], density[:400])\n",
" pred = krr.predict(features[400:])\n",
" mae = regression_metrics(density[400:],pred)['MAE']\n",
" mae = regression_metrics(density[400:],pred)['MAE'].values[0]\n",
" return mae"
]
},
Expand Down Expand Up @@ -162,45 +172,45 @@
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>(4.3428571428571425, linear, 1)</td>\n",
" <td>0.105177</td>\n",
" <td>0.001049</td>\n",
" <td>(2.928571428571429, linear, 1)</td>\n",
" <td>0.102514</td>\n",
" <td>0.000390</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>(4.3428571428571425, linear, 1)</td>\n",
" <td>0.105177</td>\n",
" <td>0.001099</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000230</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>(1.3309342128829402, linear, 1)</td>\n",
" <td>0.096677</td>\n",
" <td>0.000536</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000312</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>(1.1297049580471703, linear, 5)</td>\n",
" <td>0.095685</td>\n",
" <td>0.000572</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>(1.1297049580471703, linear, 5)</td>\n",
" <td>0.095685</td>\n",
" <td>0.001062</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000309</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Best_individual Fitness_values Time (hours)\n",
"0 (4.3428571428571425, linear, 1) 0.105177 0.001049\n",
"1 (4.3428571428571425, linear, 1) 0.105177 0.001099\n",
"2 (1.3309342128829402, linear, 1) 0.096677 0.000536\n",
"3 (1.1297049580471703, linear, 5) 0.095685 0.000572\n",
"4 (1.1297049580471703, linear, 5) 0.095685 0.001062"
"0 (2.928571428571429, linear, 1) 0.102514 0.000390\n",
"1 (1.1057547599530448, linear, 1) 0.095582 0.000230\n",
"2 (1.1057547599530448, linear, 1) 0.095582 0.000312\n",
"3 (1.1057547599530448, linear, 1) 0.095582 0.000143\n",
"4 (1.1057547599530448, linear, 1) 0.095582 0.000309"
]
},
"execution_count": 5,
Expand All @@ -221,7 +231,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"{'alpha': 1.1297049580471703, 'kernels': 'linear', 'degree': 5}\n"
"{'alpha': 1.1057547599530448, 'kernels': 'linear', 'degree': 1}\n"
]
}
],
Expand Down Expand Up @@ -281,45 +291,45 @@
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>(1.1297049580471703, linear, 5)</td>\n",
" <td>0.095685</td>\n",
" <td>0.001405</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000271</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>(1.1297049580471703, linear, 5)</td>\n",
" <td>0.095685</td>\n",
" <td>0.000581</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000260</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>(0.37125764950137985, linear, 2)</td>\n",
" <td>0.091373</td>\n",
" <td>0.000673</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000471</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>(0.37125764950137985, linear, 2)</td>\n",
" <td>0.091373</td>\n",
" <td>0.000532</td>\n",
" <td>(1.1057547599530448, linear, 1)</td>\n",
" <td>0.095582</td>\n",
" <td>0.000116</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>(0.37125764950137985, linear, 2)</td>\n",
" <td>0.091373</td>\n",
" <td>0.000353</td>\n",
" <td>(1.0210089362161252, linear, 4)</td>\n",
" <td>0.095203</td>\n",
" <td>0.000316</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Best_individual Fitness_values Time (hours)\n",
"0 (1.1297049580471703, linear, 5) 0.095685 0.001405\n",
"1 (1.1297049580471703, linear, 5) 0.095685 0.000581\n",
"2 (0.37125764950137985, linear, 2) 0.091373 0.000673\n",
"3 (0.37125764950137985, linear, 2) 0.091373 0.000532\n",
"4 (0.37125764950137985, linear, 2) 0.091373 0.000353"
" Best_individual Fitness_values Time (hours)\n",
"0 (1.1057547599530448, linear, 1) 0.095582 0.000271\n",
"1 (1.1057547599530448, linear, 1) 0.095582 0.000260\n",
"2 (1.1057547599530448, linear, 1) 0.095582 0.000471\n",
"3 (1.1057547599530448, linear, 1) 0.095582 0.000116\n",
"4 (1.0210089362161252, linear, 4) 0.095203 0.000316"
]
},
"execution_count": 8,
Expand All @@ -330,20 +340,13 @@
"source": [
"fitness_df_resume"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python [conda env:v2_0.7]",
"display_name": "Python [conda env:chemml_env] *",
"language": "python",
"name": "conda-env-v2_0.7-py"
"name": "conda-env-chemml_env-py"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -355,7 +358,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.8"
"version": "3.8.12"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
Expand Down
Binary file modified docs/ipython_notebooks/images/Parity.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading

0 comments on commit a33f050

Please sign in to comment.