Chiproject 3
Chiproject 3
Mansi Goel
drug discovery
projectcode
ihci
Document Details
Submission ID
Download Date
File Name
chiproject_3.ipynb
File Size
591.6 KB
22 Missing Citation 1%
Matches that have quotation marks, but no in-text citation
Integrity Flags
0 Integrity Flags for Review
Our system's algorithms look deeply at a document for any inconsistencies that
would set it apart from a normal submission. If we notice something strange, we flag
it for you to review.
22 Missing Citation 1%
Matches that have quotation marks, but no in-text citation
Top Sources
The sources with the highest number of matches within the submission. Overlapping sources will not be displayed.
1 Student papers
University of Huddersfield 4%
2 Internet
stankovmartin.github.io 2%
3 Internet
gist.github.com 2%
4 Student papers
Sabanci Universitesi 2%
5 Student papers
University of Sheffield 2%
6 Student papers
7 Internet
gitlab.sliit.lk 1%
8 Student papers
Birkbeck College 1%
9 Internet
peerj.com 0%
10 Publication
Di Wu. "Data Mining with Python - Theory, Application, and Case Studies", CRC Pr… 0%
11 Publication
Andre Ye, Zian Wang. "Modern Deep Learning for Tabular Data", Springer Science… 0%
12 Publication
13 Publication
Leon, Javier. "Forecasting Imported Fruit Prices in the United States Using Neural… 0%
14 Internet
pastebin.com 0%
15 Publication
16 Publication
17 Publication
18 Publication
King, Shelby Lynn. "Religious Dynamics of Secrecy in Cold War American Life", Por… 0%
19 Publication
Md Zia Uddin. "Machine Learning and Python for Human Behavior, Emotion, and … 0%
20 Publication
Pramod Gupta, Naresh Kumar Sehgal, John M. Acken. "Chapter 2 Machine Learni… 0%
21 Publication
22 Publication
23 Publication
Dirk P. Kroese, Zdravko I. Botev, Thomas Taimre, Radislav Vaisman. "Data Science… 0%
24 Publication
2 {"metadata":{"kernelspec":{"language":"python","display_name":"Python
3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype"
:"text/x-
python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3"
,"nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dat
aSources":[{"sourceId":9925115,"sourceType":"datasetVersion","datasetId":6100275}],
"dockerImageVersionId":30786,"isInternetEnabled":true,"language":"python","sourceTy
9 pe":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_ty
2 filename))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_ce
ll_guid":"b1076dfc-b9ad-4769-8c92-
a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T10:25:25.183669Z","iopub.execute_input":"2024-11-
24T10:25:25.184023Z","iopub.status.idle":"2024-11-
24T10:25:26.084459Z","shell.execute_reply.started":"2024-11-
24T10:25:25.183990Z","shell.execute_reply":"2024-11-
24T10:25:26.083352Z"}},"outputs":[{"name":"stdout","text":"/kaggle/input/solublity/chi.c
3 sv\n","output_type":"stream"}],"execution_count":1},{"cell_type":"markdown","source":"
https://www.kaggle.com/competitions/aqueous-solubility-
pandas as pd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T10:25:26.086305Z","iopub.execute_input":"2024-11-
24T10:25:26.086891Z","iopub.status.idle":"2024-11-
24T10:25:26.091021Z","shell.execute_reply.started":"2024-11-
24T10:25:26.086850Z","shell.execute_reply":"2024-11-
2 24T10:25:26.090127Z"}},"outputs":[],"execution_count":2},{"cell_type":"code","source":"
data =
pd.read_csv('/kaggle/input/solublity/chi.csv')\ndata.head(10)","metadata":{"trusted":true
,"execution":{"iopub.status.busy":"2024-11-
24T10:25:26.092066Z","iopub.execute_input":"2024-11-
24T10:25:26.092456Z","iopub.status.idle":"2024-11-
24T10:25:26.273762Z","shell.execute_reply.started":"2024-11-
24T10:25:26.092419Z","shell.execute_reply":"2024-11-
2 24T10:25:26.272642Z"}},"outputs":[{"execution_count":3,"output_type":"execute_result
<th>NumRotatableBonds</th>\n <th>NumValenceElectrons</th>\n
<th>NumAromaticRings</th>\n <th>NumSaturatedRings</th>\n
1 7-8-9-10-11-12-13-...</td>\n <td>SZEMGTQCPRNXEG-UHFFFAOYSA-M</td>\n
2 <td>[Br-].CCCCCCCCCCCCCCCCCC[N+](C)(C)C</td>\n <td>-3.616127</td>\n
one</td>\n <td>InChI=1S/C11H7NO/c13-11-8-5-1-3-7-4-2-6-9(12-1...</td>\n
1 <td>GPYLCFQEKPUWLD-UHFFFAOYSA-N</td>\n
<td>O=C1Nc2cccc3cccc1c23</td>\n <td>-3.254767</td>\n
chlorobenzaldehyde</td>\n <td>InChI=1S/C7H5ClO/c8-7-3-1-6(5-9)2-4-7/h1-
5H</td>\n <td>AVPYQKSLYISFPO-UHFFFAOYSA-N</td>\n
phenylethyl)benzo...</td>\n <td>InChI=1S/2C23H22O3.Zn/c2*1-15(17-9-5-3-6-10-
17...</td>\n <td>XTUPUYCJWKHGSW-UHFFFAOYSA-L</td>\n
3 <td>[Zn++].CC(c1ccccc1)c2cc(C(C)c3ccccc3)c(O)c(c2)...</td>\n <td>-
<td>4-({4-[bis(oxiran-2-ylmethyl)amino]phenyl}meth...</td>\n
<td>InChI=1S/C25H30N2O4/c1-5-20(26(10-22-14-28-22)...</td>\n
<td>FAUAZXVRLVIARB-UHFFFAOYSA-N</td>\n
<td>C1OC1CN(CC2CO2)c3ccc(Cc4ccc(cc4)N(CC5CO5)CC6CO...</td>\n <td>-
<td>vinyltoluene</td>\n <td>InChI=1S/C9H10/c1-3-9-6-4-5-8(2)7-9/h3-
7H,1H2,2H3</td>\n <td>JZHGRUMIRATHIU-UHFFFAOYSA-N</td>\n
<td>InChI=1S/C10H18O2/c1-2-8-3-4-9(7-8)5-6-10(11)1...</td>\n
<td>WVRFSLWCFASCIS-UHFFFAOYSA-N</td>\n
1 <td>CCC1CCC(CCC(O)=O)C1</td>\n <td>-3.286116</td>\n
tetrahydroxypregna-1,4-diene-3,20-...</td>\n <td>InChI=1S/C21H28O6/c1-19-6-5-
12(23)7-11(19)3-4-...</td>\n <td>SEKYBDYVXDAYPY-UHFFFAOYSA-N</td>\n
3 <td>CC12CC(O)C3C(CCC4=CC(=O)C=CC34C)C1CC(O)C2(O)C(...</td>\n <td>-
<td>bis(4-fluorophenyl)methanone</td>\n <td>InChI=1S/C13H8F2O/c14-11-5-1-
9(2-6-11)13(16)10...</td>\n <td>LSQARZALBDFYQZ-UHFFFAOYSA-N</td>\n
4 <td>Fc1ccc(cc1)C(=O)c2ccc(F)cc2</td>\n <td>-4.396652</td>\n
<td>InChI=1S/C20H22O5/c21-19(17-9-3-1-4-10-17)24-1...</td>\n
<td>BYQDGAVOOHIJQS-UHFFFAOYSA-N</td>\n
7 <td>O=C(OCCCOCCCOC(=O)c1ccccc1)c2ccccc2</td>\n <td>-4.595503</td>\n
columns</p>\n</div>"},"metadata":{}}],"execution_count":3},{"cell_type":"code","source
":"data.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T10:25:26.276440Z","iopub.execute_input":"2024-11-
24T10:25:26.276826Z","iopub.status.idle":"2024-11-
24T10:25:26.282601Z","shell.execute_reply.started":"2024-11-
24T10:25:26.276787Z","shell.execute_reply":"2024-11-
1 24T10:25:26.281559Z"}},"outputs":[{"execution_count":4,"output_type":"execute_result
","data":{"text/plain":"(9982,
26)"},"metadata":{}}],"execution_count":4},{"cell_type":"code","source":"data.info()","me
tadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T10:25:26.283820Z","iopub.execute_input":"2024-11-
24T10:25:26.284153Z","iopub.status.idle":"2024-11-
24T10:25:26.313733Z","shell.execute_reply.started":"2024-11-
24T10:25:26.284117Z","shell.execute_reply":"2024-11-
4 24T10:25:26.312739Z"}},"outputs":[{"name":"stdout","text":"<class
MB\n","output_type":"stream"}],"execution_count":5},{"cell_type":"code","source":"data.
columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T10:25:26.314876Z","iopub.execute_input":"2024-11-
24T10:25:26.315218Z","iopub.status.idle":"2024-11-
24T10:25:26.321944Z","shell.execute_reply.started":"2024-11-
24T10:25:26.315180Z","shell.execute_reply":"2024-11-
2 24T10:25:26.321249Z"}},"outputs":[{"execution_count":6,"output_type":"execute_result
dtype='object')"},"metadata":{}}],"execution_count":6},{"cell_type":"markdown","source":
atoms\r\nNumHAcceptorsNumber of H acceptors\r\nNumHDonorsNumber of H
electrons\r\nNumAromaticRingsNumber of aromatic
2 index","metadata":{}},{"cell_type":"code","source":"data.info()","metadata":{"trusted":tru
e,"execution":{"iopub.status.busy":"2024-11-
24T10:25:26.322853Z","iopub.execute_input":"2024-11-
24T10:25:26.323184Z","iopub.status.idle":"2024-11-
24T10:25:26.340197Z","shell.execute_reply.started":"2024-11-
24T10:25:26.323145Z","shell.execute_reply":"2024-11-
4 24T10:25:26.338980Z"}},"outputs":[{"name":"stdout","text":"<class
MB\n","output_type":"stream"}],"execution_count":7},{"cell_type":"code","source":"corr
= data.select_dtypes(include =
['int64','float64'])\ncorr.corr()","metadata":{"trusted":true,"execution":{"iopub.status.busy
":"2024-11-24T10:25:26.341530Z","iopub.execute_input":"2024-11-
24T10:25:26.341870Z","iopub.status.idle":"2024-11-
24T10:25:26.381323Z","shell.execute_reply.started":"2024-11-
24T10:25:26.341835Z","shell.execute_reply":"2024-11-
3 24T10:25:26.380192Z"}},"outputs":[{"execution_count":8,"output_type":"execute_result
<th>NumHDonors</th>\n <th>NumHeteroatoms</th>\n
<th>NumRotatableBonds</th>\n <th>NumValenceElectrons</th>\n
<th>NumAromaticRings</th>\n <th>NumSaturatedRings</th>\n
3 </tbody>\n</table>\n</div>"},"metadata":{}}],"execution_count":8},{"cell_type":"code","s
plt\nsns.heatmap(corr.corr())","metadata":{"trusted":true,"execution":{"iopub.status.bus
y":"2024-11-24T10:25:26.382620Z","iopub.execute_input":"2024-11-
24T10:25:26.382964Z","iopub.status.idle":"2024-11-
24T10:25:28.285219Z","shell.execute_reply.started":"2024-11-
24T10:25:26.382926Z","shell.execute_reply":"2024-11-
2 24T10:25:28.284085Z"}},"outputs":[{"execution_count":9,"output_type":"execute_result
","data":{"text/plain":"<Axes:
>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size
640x480 with 2
Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAApgAAAIrCAYAAABLb+kSAA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+p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"},"metadata":{}}],"execution_count":9},{"c
2 ell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":n
ull},{"cell_type":"code","source":"y =
data['Solubility']\ny.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"
2024-11-24T10:25:28.287217Z","iopub.execute_input":"2024-11-
24T10:25:28.287641Z","iopub.status.idle":"2024-11-
24T10:25:28.293441Z","shell.execute_reply.started":"2024-11-
24T10:25:28.287609Z","shell.execute_reply":"2024-11-
2 24T10:25:28.292550Z"}},"outputs":[{"execution_count":10,"output_type":"execute_resul
t","data":{"text/plain":"(9982,)"},"metadata":{}}],"execution_count":10},{"cell_type":"code
","source":"y.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-
11-24T10:25:28.294447Z","iopub.execute_input":"2024-11-
24T10:25:28.294690Z","iopub.status.idle":"2024-11-
24T10:25:28.306094Z","shell.execute_reply.started":"2024-11-
24T10:25:28.294666Z","shell.execute_reply":"2024-11-
3 24T10:25:28.305197Z"}},"outputs":[{"execution_count":11,"output_type":"execute_resul
2 float64"},"metadata":{}}],"execution_count":11},{"cell_type":"code","source":"pip install
rdkit","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T10:28:57.868252Z","iopub.execute_input":"2024-11-
24T10:28:57.868886Z","iopub.status.idle":"2024-11-
24T10:29:08.704807Z","shell.execute_reply.started":"2024-11-
24T10:28:57.868852Z","shell.execute_reply":"2024-11-
24T10:29:08.703677Z"}},"outputs":[{"name":"stdout","text":"Collecting rdkit\n
\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MB/s\u001b[0m eta
\u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hInstalling
6 packages.\n","output_type":"stream"}],"execution_count":14},{"cell_type":"code","sourc
Descriptors.TPSA(mol),\n \"NumRotatableBonds_SMILES\":
Descriptors.NumRotatableBonds(mol),\n \"NumAromaticRings_SMILES\":
Descriptors.NumAromaticRings(mol),\n \"NumValenceElectrons_SMILES\":
Descriptors.NumValenceElectrons(mol),\n \"NumHAcceptors_SMILES\":
Descriptors.NumHAcceptors(mol),\n \"NumHDonors_SMILES\":
Descriptors.NumHDonors(mol),\n \"RingCount_SMILES\":
Descriptors.RingCount(mol),\n \"BalabanJ_SMILES\":
\"NumRotatableBonds_SMILES\",\n \"NumAromaticRings_SMILES\",
\"NumValenceElectrons_SMILES\", \"NumHAcceptors_SMILES\",\n
data['SMILES'].apply(lambda x: pd.Series(calculate_smiles_descriptors(x)))],
OneHotEncoder\ncategorical_features = ['Group']\none_hot_encoder =
OneHotEncoder()\nencoded_data =
one_hot_encoder.fit_transform(data[categorical_features]).toarray()\nencoded_feature
_names = one_hot_encoder.get_feature_names(categorical_features)\ndata =
pd.concat([data.drop(columns=categorical_features), pd.DataFrame(encoded_data,
'LabuteASA']\npolynomial_transformer = PolynomialFeatures(degree=2,
include_bias=False)\ndata_interactions =
polynomial_transformer.fit_transform(data[numeric_features])\n#interaction_feature_n
ames = polynomial_transformer.get_feature_names(numeric_features)\ndata =
10 pd.concat([data.drop(columns=numeric_features), pd.DataFrame(data_interactions,
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T10:44:27.145716Z","iopub.execute_input":"2024-11-
24T10:44:27.146127Z","iopub.status.idle":"2024-11-
24T10:44:41.178017Z","shell.execute_reply.started":"2024-11-
24T10:44:27.146089Z","shell.execute_reply":"2024-11-
3 neighbors\n","output_type":"stream"},{"traceback":["\u001b[0;31m----------------------------
-----------------------------------------------\u001b[0m","\u001b[0;31mAttributeError\u001b[0m
encoded_data \u001b[38;5;241m=\u001b[39m
one_hot_encoder\u001b[38;5;241m.\u001b[39mfit_transform(data[categorical_feature
3 s])\u001b[38;5;241m.\u001b[39mtoarray()\n\u001b[0;32m---> 45\u001b[0m
encoded_feature_names \u001b[38;5;241m=\u001b[39m
3 \u001b[43mone_hot_encoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[
3 43mget_feature_names\u001b[49m(categorical_features)\n\u001b[1;32m
pd\u001b[38;5;241m.\u001b[39mconcat([data\u001b[38;5;241m.\u001b[39mdrop(colu
mns\u001b[38;5;241m=\u001b[39mcategorical_features),
pd\u001b[38;5;241m.\u001b[39mDataFrame(encoded_data,
columns\u001b[38;5;241m=\u001b[39mencoded_feature_names)],
3 axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m
3 features\u001b[39;00m\n","\u001b[0;31mAttributeError\u001b[0m: 'OneHotEncoder'
no attribute
6 'get_feature_names'","output_type":"error"}],"execution_count":16},{"cell_type":"code","
source":"print(data.columns)","metadata":{"trusted":true,"execution":{"iopub.status.busy
":"2024-11-23T22:55:52.511524Z","iopub.execute_input":"2024-11-
23T22:55:52.512427Z","iopub.status.idle":"2024-11-
23T22:55:52.521750Z","shell.execute_reply.started":"2024-11-
23T22:55:52.512385Z","shell.execute_reply":"2024-11-
6 dtype='object')\n","output_type":"stream"}],"execution_count":13},{"cell_type":"code","s
ource":"data.isnull().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"
2024-11-23T22:55:52.522800Z","iopub.execute_input":"2024-11-
23T22:55:52.523065Z","iopub.status.idle":"2024-11-
23T22:55:52.539357Z","shell.execute_reply.started":"2024-11-
23T22:55:52.523040Z","shell.execute_reply":"2024-11-
23T22:55:52.538334Z"}},"outputs":[{"execution_count":14,"output_type":"execute_resul
int64"},"metadata":{}}],"execution_count":14},{"cell_type":"code","source":"data['MolWt_
log'] =
np.log1p(data['MolWt'])\ndata['MolWt_log']","metadata":{"trusted":true,"execution":{"iop
ub.status.busy":"2024-11-23T22:55:52.540454Z","iopub.execute_input":"2024-11-
23T22:55:52.540868Z","iopub.status.idle":"2024-11-
23T22:55:52.549144Z","shell.execute_reply.started":"2024-11-
23T22:55:52.540841Z","shell.execute_reply":"2024-11-
3 23T22:55:52.548398Z"}},"outputs":[{"execution_count":15,"output_type":"execute_resul
2 dtype: float64"},"metadata":{}}],"execution_count":15},{"cell_type":"code","source":"pip
install rdkit","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
23T22:55:52.550209Z","iopub.execute_input":"2024-11-
23T22:55:52.550507Z","iopub.status.idle":"2024-11-
23T22:56:03.660928Z","shell.execute_reply.started":"2024-11-
23T22:55:52.550475Z","shell.execute_reply":"2024-11-
23T22:56:03.659781Z"}},"outputs":[{"name":"stdout","text":"Collecting rdkit\n
\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MB/s\u001b[0m eta
\u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hInstalling
6 packages.\n","output_type":"stream"}],"execution_count":16},{"cell_type":"code","sourc
Descriptors.NumRotatableBonds(mol),\n \"NumAromaticRings_SMILES\":
Descriptors.NumAromaticRings(mol),\n \"NumValenceElectrons_SMILES\":
Descriptors.NumValenceElectrons(mol),\n \"NumHAcceptors_SMILES\":
Descriptors.NumHAcceptors(mol),\n \"NumHDonors_SMILES\":
Descriptors.NumHDonors(mol),\n \"RingCount_SMILES\":
Descriptors.RingCount(mol),\n \"BalabanJ_SMILES\":
\"NumRotatableBonds_SMILES\",\n \"NumAromaticRings_SMILES\",
\"NumValenceElectrons_SMILES\", \"NumHAcceptors_SMILES\",\n
data['SMILES'].apply(lambda x: pd.Series(calculate_smiles_descriptors(x)))\ndata =
OneHotEncoder\ncategorical_features = ['Group']\none_hot_encoder =
OneHotEncoder()\nencoded_features =
one_hot_encoder.fit_transform(data[categorical_features]).toarray()\nencoded_feature
_names = one_hot_encoder.get_feature_names_out(categorical_features)\ndata =
data.drop(columns=categorical_features)\ndata = pd.concat([data,
PolynomialFeatures(degree=2, include_bias=False)\nnumeric_features =
polynomial_transformer.fit_transform(data[numeric_features])\ninteraction_feature_na
mes = polynomial_transformer.get_feature_names_out(numeric_features)\ndata =
data.drop(columns=numeric_features)\ndata = pd.concat([data,
10 pd.DataFrame(data_interactions, columns=interaction_feature_names)],
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
23T23:13:58.476193Z","iopub.execute_input":"2024-11-
23T23:13:58.476851Z","iopub.status.idle":"2024-11-
23T23:21:31.104331Z","shell.execute_reply.started":"2024-11-
23T23:13:58.476816Z","shell.execute_reply":"2024-11-
2 0.7666\n","output_type":"stream"}],"execution_count":20},{"cell_type":"code","source":"
17 RandomForestRegressor(max_depth=10, min_samples_leaf=2,
15
11 xgb.XGBRegressor(n_estimators=500, random_state=42),\n 'SVR': SVR(kernel='rbf',
{r2:.4f}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
23T23:22:16.493027Z","iopub.execute_input":"2024-11-
23T23:22:16.494077Z","iopub.status.idle":"2024-11-
23T23:24:56.709623Z","shell.execute_reply.started":"2024-11-
23T23:22:16.494035Z","shell.execute_reply":"2024-11-
23T23:24:56.708608Z"}},"outputs":[{"name":"stdout","text":"Random Forest
1.3036, R²:
2 0.7597\n","output_type":"stream"}],"execution_count":21},{"cell_type":"code","source":"
9 ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","sou
estimator\nbagging_regressor =
BaggingRegressor(base_estimator=DecisionTreeRegressor(), n_estimators=100,
12 random_state=42)\nbagging_regressor.fit(X_train, y_train)\ny_pred_bagging =
bagging_regressor.predict(X_test)\nmse_bagging = mean_squared_error(y_test,
GradientBoostingRegressor(n_estimators=100,
12 random_state=42)\nboosting_regressor.fit(X_train, y_train)\ny_pred_boosting =
boosting_regressor.predict(X_test)\nmse_boosting = mean_squared_error(y_test,
24 y_pred_boosting)\nr2_boosting = r2_score(y_test,
9 y_pred_boosting)\n\nxgboost_regressor = xgb.XGBRegressor(n_estimators=100,
random_state=42)\nxgboost_regressor.fit(X_train, y_train)\ny_pred_xgboost =
4 xgboost_regressor.predict(X_test)\nmse_xgboost = mean_squared_error(y_test,
MSE = {mse_xgboost:.4f}, R² =
{r2_xgboost:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-
11-23T23:31:22.607918Z","iopub.execute_input":"2024-11-
23T23:31:22.608282Z","iopub.status.idle":"2024-11-
23T23:31:43.880301Z","shell.execute_reply.started":"2024-11-
23T23:31:22.608248Z","shell.execute_reply":"2024-11-
2 23T23:31:43.878071Z"}},"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/sit
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging Regressor
9 0.7725\n","output_type":"stream"}],"execution_count":27},{"cell_type":"code","source":"f
ensembles.items()])\nvoting_regressor.fit(X_train, y_train)\ny_pred =
{mse:.4f}, R²:
{r2:.4f}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
23T23:38:35.560645Z","iopub.execute_input":"2024-11-
23T23:38:35.561051Z","iopub.status.idle":"2024-11-
23T23:40:13.988347Z","shell.execute_reply.started":"2024-11-
23T23:38:35.561020Z","shell.execute_reply":"2024-11-
1.2340, R²:
3 0.7725\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (SVR) -
3 0.7498\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n/opt/conda/lib/python3.10/site-
2 assume_a=\"pos\", overwrite_a=True).T\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
assume_a=\"pos\",
overwrite_a=True).T\n","output_type":"stream"},{"name":"stdout","text":"\nComposite
3 0.7528\n","output_type":"stream"}],"execution_count":29},{"cell_type":"code","source":"f
has been executed and 'top_models' has the names of the top 3 models\n\n# Extract
model in top_models]\n\n# Filter the original ensembles dictionary to include only the
= {r2_top:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
23T23:44:42.028877Z","iopub.execute_input":"2024-11-
23T23:44:42.029598Z","iopub.status.idle":"2024-11-
23T23:45:03.084319Z","shell.execute_reply.started":"2024-11-
23T23:44:42.029565Z","shell.execute_reply":"2024-11-
6 0.7847\n","output_type":"stream"}],"execution_count":30},{"cell_type":"code","source":"i
Descriptors.NumRotatableBonds(mol),\n \"NumAromaticRings_SMILES\":
Descriptors.NumAromaticRings(mol),\n \"NumValenceElectrons_SMILES\":
Descriptors.NumValenceElectrons(mol),\n \"NumHAcceptors_SMILES\":
Descriptors.NumHAcceptors(mol),\n \"NumHDonors_SMILES\":
Descriptors.NumHDonors(mol),\n \"RingCount_SMILES\":
Descriptors.RingCount(mol),\n \"BalabanJ_SMILES\":
\"NumRotatableBonds_SMILES\",\n \"NumAromaticRings_SMILES\",
\"NumValenceElectrons_SMILES\", \"NumHAcceptors_SMILES\",\n
data['SMILES'].apply(lambda x: pd.Series(calculate_smiles_descriptors(x)))\ndata =
variables\ncategorical_features = ['Group']\none_hot_encoder =
OneHotEncoder()\nencoded_features =
one_hot_encoder.fit_transform(data[categorical_features]).toarray()\nencoded_feature
_names = one_hot_encoder.get_feature_names_out(categorical_features)\ndata =
data.drop(columns=categorical_features)\ndata = pd.concat([data,
PolynomialFeatures(degree=2, include_bias=False)\nnumeric_features =
polynomial_transformer.fit_transform(data[numeric_features])\ninteraction_feature_na
mes = polynomial_transformer.get_feature_names_out(numeric_features)\ndata =
data.drop(columns=numeric_features)\ndata = pd.concat([data,
data.corr()\ncorrelation_with_target =
correlation_matrix['Solubility'].abs().sort_values(ascending=False)\nselected_features
6 features with correlation above 0.1\n\n# Split the data into training and testing sets\nX
features:\")\nprint(f\"MSE: {mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T00:11:15.250784Z","iopub.execute_input":"2024-11-
24T00:11:15.251620Z","iopub.status.idle":"2024-11-
24T00:14:01.682899Z","shell.execute_reply.started":"2024-11-
24T00:11:15.251586Z","shell.execute_reply":"2024-11-
2 0.7464\n","output_type":"stream"}],"execution_count":31},{"cell_type":"code","source":"f
has been executed and 'top_models' has the names of the top 3 models\n\n# Extract
model in top_models]\n\n# Filter the original ensembles dictionary to include only the
= {r2_top:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
24T00:14:01.684993Z","iopub.execute_input":"2024-11-
24T00:14:01.685675Z","iopub.status.idle":"2024-11-
24T00:14:15.941487Z","shell.execute_reply.started":"2024-11-
24T00:14:01.685630Z","shell.execute_reply":"2024-11-
6 0.7611\n","output_type":"stream"}],"execution_count":32},{"cell_type":"code","source":"
","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","sou
2 rce":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code
","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":
"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_
2 type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{
"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":
null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_c
Descriptors.NumRotatableBonds(mol),\n \"NumAromaticRings_SMILES\":
Descriptors.NumAromaticRings(mol),\n \"NumValenceElectrons_SMILES\":
Descriptors.NumValenceElectrons(mol),\n \"NumHAcceptors_SMILES\":
Descriptors.NumHAcceptors(mol),\n \"NumHDonors_SMILES\":
Descriptors.NumHDonors(mol),\n \"RingCount_SMILES\":
Descriptors.RingCount(mol),\n \"BalabanJ_SMILES\":
separate columns\nsmiles_descriptors_df =
'NumAromaticRings_SMILES',\n 'NumValenceElectrons_SMILES',
'BalabanJ_SMILES'\n]\n\nX = data_combined[descriptor_columns]\ny =
6 values if any (although your data seems to have no nulls)\n\n# Split into training and
RandomForest\nlinear_regressor = LinearRegression()\nrandom_forest =
17 RandomForestRegressor(n_estimators=300, random_state=42)\nboosted_rf =
10 AdaBoostRegressor(base_estimator=RandomForestRegressor(n_estimators=100),
n_estimators=300, random_state=42)\ndecision_tree =
DecisionTreeRegressor(random_state=42)\nxgboost_model =
11 xgb.XGBRegressor(n_estimators=300, random_state=42)\ngradient_boosting =
gradient_boosting),\n]\n\nmeta_model =
10 model\nstacking_regressor = StackingRegressor(estimators=base_models,
4 regressor\ny_pred = stacking_regressor.predict(X_test)\nmse =
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
21T09:19:11.659289Z","iopub.execute_input":"2024-11-
21T09:19:11.659993Z"}},"outputs":[{"name":"stdout","text":" ID
2 neighbors\n/opt/conda/lib/python3.10/site-packages/sklearn/ensemble/_base.py:166:
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
2 warnings.warn(\n","output_type":"stream"}],"execution_count":null},{"cell_type":"markd
LEARNING Performanc
6 ","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"e
6 pca.fit_transform(X_scaled)\n\n# Splitting the dataset into the Training set and Test
17 data\nstacking_regressor.fit(X_train_pca, y_train)\ny_pred_pca =
1 stacking_regressor.predict(X_test_pca)\nmse_pca = mean_squared_error(y_test,
{r2_pca:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
21T06:33:40.714368Z","iopub.execute_input":"2024-11-
21T06:33:40.714720Z","iopub.status.idle":"2024-11-
21T07:11:40.837371Z","shell.execute_reply.started":"2024-11-
21T06:33:40.714690Z","shell.execute_reply":"2024-11-
2 21T07:11:40.836329Z"}},"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/sit
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"PCA Stacking
0.7411\n","output_type":"stream"}],"execution_count":6},{"cell_type":"markdown","sour
f\"{significant_features[i]}_x_{significant_features[j]}\"\n interaction_dict[col_name]
7 AdaBoostRegressor(base_estimator=RandomForestRegressor(n_estimators=100),
DecisionTreeRegressor(random_state=42)),\n ('xgb',
9 final_estimator=GradientBoostingRegressor(n_estimators=100,
model\ny_pred = stacking_regressor.predict(X_test)\nmse =
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
21T07:35:37.695919Z","iopub.execute_input":"2024-11-
21T07:35:37.696867Z","iopub.status.idle":"2024-11-
21T09:10:43.630290Z","shell.execute_reply.started":"2024-11-
21T07:35:37.696820Z","shell.execute_reply":"2024-11-
2 21T09:10:43.629360Z"}},"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/sit
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
2 warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"\nStacking
6 0.7665\n","output_type":"stream"}],"execution_count":14},{"cell_type":"code","source":"i
'Solubility']\nfeatures.append('SMILES')\nfeatures\n\nx=
10 LinearRegression()\nrandom_forest = RandomForestRegressor(n_estimators=500,
random_state=42)\ndecision_tree =
DecisionTreeRegressor(random_state=42)\nxgboost_model =
11 xgb.XGBRegressor(n_estimators=500, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=500, random_state=42)\nsvr =
3 {metrics['R²']:.4f}\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"c
1
6 numpy as np\nfrom sklearn.model_selection import train_test_split\nfrom
'Solubility']\nfeatures.append('SMILES')\nfeatures\n\nx= data[features]\nx.head() #
models\nlinear_regressor = LinearRegression()\nrandom_forest =
10 RandomForestRegressor(n_estimators=200, random_state=42)\ndecision_tree =
DecisionTreeRegressor(random_state=42)\nxgboost_model =
11 xgb.XGBRegressor(n_estimators=200, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=200, random_state=42)\nsvr =
{metrics['R²']:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024
-11-20T17:32:44.152727Z","iopub.execute_input":"2024-11-
20T17:32:44.153057Z","iopub.status.idle":"2024-11-
20T17:32:55.884671Z","shell.execute_reply.started":"2024-11-
20T17:32:44.153029Z","shell.execute_reply":"2024-11-
3.0517, R²: 0.4374\nRandom Forest - MSE: 1.8172, R²: 0.6650\nDecision Tree - MSE:
3.0517, R²: 0.4374\nRandom Forest - MSE: 1.8172, R²: 0.6650\nDecision Tree - MSE:
1.7574, R²:
6 0.6760\n","output_type":"stream"}],"execution_count":42},{"cell_type":"code","source":"i
10 LinearRegression()\nrandom_forest = RandomForestRegressor(n_estimators=200,
random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=200, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=200, random_state=42)\nsvr =
10 svr)\n]\n\nmeta_model = GradientBoostingRegressor(n_estimators=100,
random_state=42) # Meta-model\nstacking_regressor =
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:34:32.052094Z","iopub.execute_input":"2024-11-
20T17:34:32.052733Z","iopub.status.idle":"2024-11-
20T17:36:31.657928Z","shell.execute_reply.started":"2024-11-
20T17:34:32.052698Z","shell.execute_reply":"2024-11-
20T17:36:31.656807Z"}},"outputs":[{"name":"stdout","text":"\nStacking Regressor
Performance:\nMSE: 1.1573\nR²:
2 0.7867\n","output_type":"stream"}],"execution_count":45},{"cell_type":"code","source":"
","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","sou
rce":"correlations =
corr.corrwith(corr['Solubility'])\ncorrelations","metadata":{"trusted":true,"execution":{"iop
ub.status.busy":"2024-11-20T17:27:04.505123Z","iopub.status.idle":"2024-11-
20T17:27:04.505414Z","shell.execute_reply.started":"2024-11-
20T17:27:04.505272Z","shell.execute_reply":"2024-11-
2 20T17:27:04.505288Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source
":"print(data.columns)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"202
4-11-20T17:27:04.506602Z","iopub.status.idle":"2024-11-
20T17:27:04.506940Z","shell.execute_reply.started":"2024-11-
20T17:27:04.506768Z","shell.execute_reply":"2024-11-
20T17:27:04.506783Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source
'Solubility']\nfeatures.append('SMILES')\nfeatures","metadata":{"trusted":true,"executio
n":{"iopub.status.busy":"2024-11-20T17:27:04.508073Z","iopub.status.idle":"2024-11-
20T17:27:04.508338Z","shell.execute_reply.started":"2024-11-
20T17:27:04.508207Z","shell.execute_reply":"2024-11-
20T17:27:04.508221Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source
'Solubility']\nfeatures.append('SMILES')\nfeatures\n\nx=
data[features]\nx.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2
024-11-20T17:27:04.509477Z","iopub.status.idle":"2024-11-
20T17:27:04.509818Z","shell.execute_reply.started":"2024-11-
20T17:27:04.509674Z","shell.execute_reply":"2024-11-
14 20T17:27:04.509690Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source
Dataset,
DataLoader","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:27:04.510705Z","iopub.status.idle":"2024-11-
20T17:27:04.511036Z","shell.execute_reply.started":"2024-11-
20T17:27:04.510854Z","shell.execute_reply":"2024-11-
20T17:27:04.510869Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source
42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:27:04.512312Z","iopub.status.idle":"2024-11-
20T17:27:04.512759Z","shell.execute_reply.started":"2024-11-
20T17:27:04.512535Z","shell.execute_reply":"2024-11-
6 20T17:27:04.512560Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source
models\nlinear_regressor = LinearRegression()\nrandom_forest =
10 RandomForestRegressor(n_estimators=300, random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=300, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=300, random_state=42)\nsvr =
10 model\nstacking_regressor = StackingRegressor(estimators=base_models,
stacking_regressor.predict(X_test.drop('SMILES',axis =1))\nmse =
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:41:42.961694Z","iopub.execute_input":"2024-11-
20T17:41:42.962571Z","iopub.status.idle":"2024-11-
20T17:42:18.491744Z","shell.execute_reply.started":"2024-11-
20T17:41:42.962508Z","shell.execute_reply":"2024-11-
20T17:42:18.490806Z"}},"outputs":[{"name":"stdout","text":"\nStacking Regressor
Performance:\nMSE: 1.6697\nR²:
0.6922\n","output_type":"stream"}],"execution_count":49},{"cell_type":"markdown","sou
rce":"Custom MOdel for CHEMBERT accept both smiles embedding and other
molculer feature","metadata":{}},{"cell_type":"markdown","source":"Trianing
2 MOdel","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"output
s":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"
6 outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as
plt","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:42:18.493455Z","iopub.execute_input":"2024-11-
20T17:42:18.493747Z","iopub.status.idle":"2024-11-
20T17:42:18.498193Z","shell.execute_reply.started":"2024-11-
20T17:42:18.493720Z","shell.execute_reply":"2024-11-
6 20T17:42:18.497354Z"}},"outputs":[],"execution_count":50},{"cell_type":"code","source"
:"# Split the data into training and testing sets\nxtrain, xtest, ytrain, ytest =
model\nlinear_regressor =
R²: {r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:42:18.499223Z","iopub.execute_input":"2024-11-
20T17:42:18.499473Z","iopub.status.idle":"2024-11-
20T17:42:18.518709Z","shell.execute_reply.started":"2024-11-
20T17:42:18.499449Z","shell.execute_reply":"2024-11-
3 0.4374\n","output_type":"stream"}],"execution_count":51},{"cell_type":"code","source":"f
5 the data into training and testing sets\nxtrain, xtest, ytrain, ytest = train_test_split(x, y,
{r2:.4f}\")\nprint(f\"Training R²:
{r2_train:.4f}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:42:18.520324Z","iopub.execute_input":"2024-11-
20T17:42:18.520599Z","iopub.status.idle":"2024-11-
20T17:42:18.538850Z","shell.execute_reply.started":"2024-11-
20T17:42:18.520571Z","shell.execute_reply":"2024-11-
2 0.3802\n","output_type":"stream"}],"execution_count":52},{"cell_type":"code","source":"f
matplotlib.pyplot as
plt","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:42:18.540032Z","iopub.execute_input":"2024-11-
20T17:42:18.541180Z","iopub.status.idle":"2024-11-
20T17:42:18.548580Z","shell.execute_reply.started":"2024-11-
20T17:42:18.541124Z","shell.execute_reply":"2024-11-
6 20T17:42:18.547199Z"}},"outputs":[],"execution_count":53},{"cell_type":"code","source"
matplotlib.pyplot as plt\n\n# Assuming your 'data' DataFrame has been prepared with
5 'Solubility' as the target column\n# and 'features' for the input columns.\n\n\n# Split the
5 data into training and testing sets\nxtrain, xtest, ytrain, ytest = train_test_split(x, y,
10 LinearRegression()\nrandom_forest = RandomForestRegressor(n_estimators=500,
7 random_state=42)\nxgboost_model = xgb.XGBRegressor(n_estimators=500,
RandomForest, and Linear Regression) - Test Mean Squared Error: {mse:.4f}, R²:
plt.ylabel('Solubility')\n
plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:42:18.549465Z","iopub.execute_input":"2024-11-
20T17:42:18.549800Z","iopub.status.idle":"2024-11-
20T17:42:28.023670Z","shell.execute_reply.started":"2024-11-
20T17:42:18.549765Z","shell.execute_reply":"2024-11-
6 0.8588\n","output_type":"stream"}],"execution_count":54},{"cell_type":"code","source":"i
5 data into training and testing sets\nxtrain, xtest, ytrain, ytest = train_test_split(x, y,
RandomForestRegressor(n_estimators=500, random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=500, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=500, random_state=42)\nsvr =
pd.DataFrame(results).T\nprint(\"\\nSummary of Results:\")\nprint(results_df)\n\n#
plt.xlabel('Feature')\n plt.ylabel('Solubility')\n
plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:42:28.024808Z","iopub.execute_input":"2024-11-
20T17:42:28.025057Z","iopub.status.idle":"2024-11-
20T17:42:57.271685Z","shell.execute_reply.started":"2024-11-
20T17:42:28.025031Z","shell.execute_reply":"2024-11-
R²: 0.3802, Test R²: 0.4374, Test MSE: 3.0517\nRandom Forest - Train R²: 0.9442,
Test R²: 0.6660, Test MSE: 1.8118\nDecision Tree - Train R²: 0.9858, Test R²: 0.4615,
Test MSE: 2.9211\nXGBoost - Train R²: 0.9292, Test R²: 0.5964, Test MSE:
2.1895\nGradient Boosting - Train R²: 0.7734, Test R²: 0.6848, Test MSE:
1.7099\nSVR - Train R²: 0.6424, Test R²: 0.6552, Test MSE: 1.8702\nVoting
Regressor - Train R²: 0.8997, Test R²: 0.6722, Test MSE: 1.7782\n\nSummary of
2 0.672202\n","output_type":"stream"}],"execution_count":55},{"cell_type":"code","source
":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","s
models\nlinear_regressor = LinearRegression()\nrandom_forest =
RandomForestRegressor(n_estimators=500, random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=500, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=500, random_state=42)\nsvr =
Bagging\nbagging_regressor_lr =
11 BaggingRegressor(base_estimator=linear_regressor, n_estimators=50,
random_state=42)\nbagging_regressor_dt =
11 BaggingRegressor(base_estimator=decision_tree, n_estimators=50,
random_state=42)\nbagging_regressor_svr = BaggingRegressor(base_estimator=svr,
pd.DataFrame(results).T\nprint(\"\\nSummary of Results:\")\nprint(results_df)\n\n#
plt.xlabel('Feature')\n plt.ylabel('Solubility')\n
plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:42:57.273230Z","iopub.execute_input":"2024-11-
20T17:42:57.273547Z","iopub.status.idle":"2024-11-
20T17:45:20.799185Z","shell.execute_reply.started":"2024-11-
20T17:42:57.273502Z","shell.execute_reply":"2024-11-
R²: 0.3802, Test R²: 0.4374, Test MSE: 3.0517\nRandom Forest - Train R²: 0.9442,
Test R²: 0.6660, Test MSE: 1.8118\nDecision Tree - Train R²: 0.9858, Test R²: 0.4615,
Test MSE: 2.9211\nXGBoost - Train R²: 0.9292, Test R²: 0.5964, Test MSE:
2.1895\nGradient Boosting - Train R²: 0.7734, Test R²: 0.6848, Test MSE:
1.7099\nSVR - Train R²: 0.6424, Test R²: 0.6552, Test MSE: 1.8702\nBagging (Linear
3 3.0508\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (Decision
3 1.8403\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (SVR) -
Train R²: 0.6432, Test R²: 0.6556, Test MSE: 1.8684\n\nSummary of Results:\n
9 0.655572\n","output_type":"stream"}],"execution_count":56},{"cell_type":"code","source
21 np\n\n# Assuming x and y are defined (data and target)\n\n# Scale the features
models\nlinear_regressor = LinearRegression()\nrandom_forest =
RandomForestRegressor(n_estimators=500, random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=500, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=500, random_state=42)\nsvr =
11 BaggingRegressor(base_estimator=linear_regressor, n_estimators=50,
random_state=42)\nbagging_regressor_dt =
11 BaggingRegressor(base_estimator=decision_tree, n_estimators=50,
random_state=42)\nbagging_regressor_svr = BaggingRegressor(base_estimator=svr,
pd.DataFrame(results).T\nprint(\"\\nSummary of Results:\")\nprint(results_df)\n\n#
plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:45:20.800888Z","iopub.execute_input":"2024-11-
20T17:45:20.801449Z","iopub.status.idle":"2024-11-
20T17:49:16.400019Z","shell.execute_reply.started":"2024-11-
20T17:45:20.801407Z","shell.execute_reply":"2024-11-
R²: 0.3802, Test R²: 0.4374, Test MSE: 3.0517\nRandom Forest - Train R²: 0.9442,
Test R²: 0.6660, Test MSE: 1.8118\nDecision Tree - Train R²: 0.9858, Test R²: 0.4615,
Test MSE: 2.9211\nXGBoost - Train R²: 0.9292, Test R²: 0.5964, Test MSE:
2.1895\nGradient Boosting - Train R²: 0.7734, Test R²: 0.6848, Test MSE:
1.7099\nSVR - Train R²: 0.6424, Test R²: 0.6552, Test MSE: 1.8702\nBagging (Linear
3 3.0508\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (Decision
3 1.8403\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
7 warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (SVR) -
Train R²: 0.6432, Test R²: 0.6556, Test MSE: 1.8684\nVoting Regressor - Train R²:
0.8750, Test R²: 0.6831, Test MSE: 1.7190\nStacking Regressor - Train R²: 0.8104,
1.710930
9 0.684601\n","output_type":"stream"}],"execution_count":57},{"cell_type":"code","source
21 np\n\n# Assuming x and y are defined (data and target)\n\n# Scale the features
models\nlinear_regressor = LinearRegression()\nrandom_forest =
RandomForestRegressor(n_estimators=200, random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=200, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=200, random_state=42)\nsvr =
11 BaggingRegressor(base_estimator=linear_regressor, n_estimators=50,
random_state=42)\nbagging_regressor_dt =
11 BaggingRegressor(base_estimator=decision_tree, n_estimators=50,
random_state=42)\nbagging_regressor_svr = BaggingRegressor(base_estimator=svr,
pd.DataFrame(results).T\nprint(\"\\nSummary of Results:\")\nprint(results_df)\n\n#
plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:49:16.403239Z","iopub.execute_input":"2024-11-
20T17:49:16.403535Z","iopub.status.idle":"2024-11-
20T17:52:23.582022Z","shell.execute_reply.started":"2024-11-
20T17:49:16.403491Z","shell.execute_reply":"2024-11-
R²: 0.3802, Test R²: 0.4374, Test MSE: 3.0517\nRandom Forest - Train R²: 0.9438,
Test R²: 0.6649, Test MSE: 1.8179\nDecision Tree - Train R²: 0.9858, Test R²: 0.4615,
Test MSE: 2.9211\nXGBoost - Train R²: 0.8777, Test R²: 0.6377, Test MSE:
1.9652\nGradient Boosting - Train R²: 0.7303, Test R²: 0.6895, Test MSE:
1.6842\nSVR - Train R²: 0.6424, Test R²: 0.6552, Test MSE: 1.8702\nBagging (Linear
3 3.0508\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (Decision
3 1.8403\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (SVR) -
Train R²: 0.6432, Test R²: 0.6556, Test MSE: 1.8684\nVoting Regressor - Train R²:
0.8567, Test R²: 0.6851, Test MSE: 1.7081\nStacking Regressor - Train R²: 0.7932,
1.711092
3 0.684571\n","output_type":"stream"}],"execution_count":58},{"cell_type":"code","source
RandomForestRegressor(n_estimators = 300,random_state =
42)\nrandomclassifer.fit(xtrain.drop('SMILES',axis =1),ytrain)\nyprediction =
randomclassifer.predict(xtest.drop('SMILES',axis =1))\nRMSE =
Error',RMSE)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:52:23.583165Z","iopub.execute_input":"2024-11-
20T17:52:23.583492Z","iopub.status.idle":"2024-11-
20T17:52:28.477749Z","shell.execute_reply.started":"2024-11-
20T17:52:23.583465Z","shell.execute_reply":"2024-11-
1.3470874186947464\n","output_type":"stream"}],"execution_count":59},{"cell_type":"c
squared (R²):
{R2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:52:28.478900Z","iopub.execute_input":"2024-11-
20T17:52:28.479252Z","iopub.status.idle":"2024-11-
20T17:52:28.632968Z","shell.execute_reply.started":"2024-11-
20T17:52:28.479215Z","shell.execute_reply":"2024-11-
20T17:52:28.632018Z"}},"outputs":[{"name":"stdout","text":"Model Performance:\nRoot
(R²):
3 0.6655\n","output_type":"stream"}],"execution_count":60},{"cell_type":"code","source":"f
squared: {R2:.4f}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-
11-20T17:52:28.634102Z","iopub.execute_input":"2024-11-
20T17:52:28.634361Z","iopub.status.idle":"2024-11-
20T17:52:28.995370Z","shell.execute_reply.started":"2024-11-
20T17:52:28.634336Z","shell.execute_reply":"2024-11-
3 0.6752\n","output_type":"stream"}],"execution_count":61},{"cell_type":"code","source":"f
1 [100, 200, 500],\n 'max_depth': [5, 10, 15],\n 'min_samples_split': [2, 5, 10],\n
grid_search.best_estimator_\nprint(\"Best Parameters:\",
grid_search.best_params_)","metadata":{"trusted":true,"execution":{"iopub.status.busy"
:"2024-11-20T17:52:28.998233Z","iopub.execute_input":"2024-11-
20T17:52:28.998491Z","iopub.status.idle":"2024-11-
20T17:55:25.766750Z","shell.execute_reply.started":"2024-11-
20T17:52:28.998465Z","shell.execute_reply":"2024-11-
1 20T17:55:25.765607Z"}},"outputs":[{"name":"stdout","text":"Best Parameters:
6 500}\n","output_type":"stream"}],"execution_count":62},{"cell_type":"code","source":"fro
scores.mean())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:55:25.768057Z","iopub.execute_input":"2024-11-
20T17:55:25.768349Z","iopub.status.idle":"2024-11-
20T17:55:45.243947Z","shell.execute_reply.started":"2024-11-
20T17:55:25.768319Z","shell.execute_reply":"2024-11-
20T17:55:45.243052Z"}},"outputs":[{"name":"stdout","text":"Cross-validated R² scores:
2 0.6610386627686335\n","output_type":"stream"}],"execution_count":63},{"cell_type":"c
y')\nplt.legend()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy"
:"2024-11-20T17:55:45.245113Z","iopub.execute_input":"2024-11-
20T17:55:45.245476Z","iopub.status.idle":"2024-11-
20T17:55:45.561134Z","shell.execute_reply.started":"2024-11-
20T17:55:45.245437Z","shell.execute_reply":"2024-11-
2 20T17:55:45.560302Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<
Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAj4AAAHHCAYAAAC/R1LgA
AAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6
Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABqJUl
EQVR4nO3deXhT1fY38G8SOtOmMylQaMskpcxYqCDzUEEuqJcrODBcREFABidwAl
QEr3pFRVFRwVdwuI4ISJF5sghSplpAKC0gtCAtbaGlU3LeP/pLbNoMJ2mSc5J8P8/T5
yHJyclqmnJW9157L4UgCAKIiIiIvIBS6gCIiIiIXIWJDxEREXkNJj5ERETkNZj4EBERkdd
g4kNEREReg4kPEREReQ0mPkREROQ1mPgQERGR12DiQ0RERF6DiQ8R2WThwo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1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NJj5ERETkNf4/At/HbDIi0r8AAAAASUVORK5CYII="},"metadata":{}}],"execution_count
2 ":64},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_c
SVR(kernel='linear')\nlinear_svr.fit(xtrain.drop('SMILES',axis =1),
2 {r2_linear:.4f}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_ty
matplotlib\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:59:19.218987Z","iopub.execute_input":"2024-11-
20T17:59:19.219792Z","iopub.status.idle":"2024-11-
20T17:59:28.221175Z","shell.execute_reply.started":"2024-11-
20T17:59:19.219745Z","shell.execute_reply":"2024-11-
8 20T17:59:28.220166Z"}},"outputs":[{"name":"stdout","text":"Requirement already
6 packages.\n","output_type":"stream"}],"execution_count":17},{"cell_type":"code","sourc
plt\n\n# Assume 'data' is your DataFrame loaded from a CSV or another source\n# #
with your actual data loading code\n# data = pd.DataFrame({\n# 'SMILES': ['C', 'CC',
'CCC', 'CCCC', 'CCCCC'],\n# 'Solubility': [0.1, -0.2, 0.3, -0.4, 0.5],\n# 'Feature1':
[1.2, 3.4, 5.6, 7.8, 9.0],\n# 'Feature2': [0.1, 0.2, 0.3, 0.4, 0.5]\n# })\n# correlations =
'Solubility']\nfeatures.append('SMILES')\n\nx = data[features]\ny =
random_state=42)\n\n# Scale the features (important for SVR and some other
10 models)\nscaler = StandardScaler()\nX_train_scaled =
10 scaler.fit_transform(X_train.drop('SMILES', axis=1))\nX_test_scaled =
models\nlinear_regressor = LinearRegression()\nrandom_forest =
10 RandomForestRegressor(n_estimators=200, random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=200, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=200, random_state=42)\nsvr =
and stacking\nbagging_regressor_lr =
11 BaggingRegressor(base_estimator=linear_regressor, n_estimators=50,
random_state=42)\nbagging_regressor_dt =
11 BaggingRegressor(base_estimator=decision_tree, n_estimators=50,
random_state=42)\nbagging_regressor_svr = BaggingRegressor(base_estimator=svr,
11 n_estimators=50, random_state=42)\nvoting_regressor =
7 final_estimator=RandomForestRegressor(n_estimators=200,
plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T17:59:29.432275Z","iopub.execute_input":"2024-11-
20T17:59:29.433003Z","iopub.status.idle":"2024-11-
20T18:01:33.904909Z","shell.execute_reply.started":"2024-11-
20T17:59:29.432967Z","shell.execute_reply":"2024-11-
MSE: 3.0517, Test R²: 0.4374\nRandom Forest - Test MSE: 1.8179, Test R²:
0.6649\nDecision Tree - Test MSE: 2.9211, Test R²: 0.4615\nXGBoost - Test MSE:
1.9652, Test R²: 0.6377\nGradient Boosting - Test MSE: 1.6842, Test R²:
0.6895\nSVR - Test MSE: 1.8702, Test R²: 0.6552\nBagging (LR) - Test MSE: 3.0508,
Test R²:
3 0.4376\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n/opt/conda/lib/python3.10/site-
3 0.6607\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"Bagging (SVR) -
Test MSE: 1.8684, Test R²: 0.6556\nVoting Regressor - Test MSE: 1.7081, Test R²:
2 0.6846\n","output_type":"stream"}],"execution_count":18},{"cell_type":"code","source":"f
X_test, y_test, base_models, final_model):\n # Container for base models that are
fitted\n trained_models = []\n \n # Initial features are just the original training
Sequentially train base models and stack predictions\n for model in base_models:\n
10 cloned_model.fit(current_train_features, y_train)\n
demonstration\nbase_models = [LinearRegression(),
sequential_meta_boosting function\nmse, r2 =
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T18:03:28.958698Z","iopub.execute_input":"2024-11-
20T18:03:28.959467Z","iopub.status.idle":"2024-11-
20T18:03:32.469364Z","shell.execute_reply.started":"2024-11-
20T18:03:28.959434Z","shell.execute_reply":"2024-11-
R²:
3 0.6137\n","output_type":"stream"}],"execution_count":20},{"cell_type":"code","source":"\
y, test_size=0.2,
random_state=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-
11-20T18:22:05.252553Z","iopub.execute_input":"2024-11-
20T18:22:05.252893Z","iopub.status.idle":"2024-11-
20T18:22:05.262843Z","shell.execute_reply.started":"2024-11-
20T18:22:05.252862Z","shell.execute_reply":"2024-11-
20T18:22:05.261975Z"}},"outputs":[],"execution_count":35},{"cell_type":"code","source"
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T18:22:05.859150Z","iopub.execute_input":"2024-11-
20T18:22:05.859895Z","iopub.status.idle":"2024-11-
20T18:24:46.584242Z","shell.execute_reply.started":"2024-11-
20T18:22:05.859860Z","shell.execute_reply":"2024-11-
2 20T18:24:46.583199Z"}},"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/sit
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"MSE: 1.3050\nR²:
2 0.7594\n","output_type":"stream"}],"execution_count":36},{"cell_type":"code","source":"f
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T18:25:16.292215Z","iopub.execute_input":"2024-11-
20T18:25:16.292545Z","iopub.status.idle":"2024-11-
20T18:30:42.177717Z","shell.execute_reply.started":"2024-11-
20T18:25:16.292516Z","shell.execute_reply":"2024-11-
2 20T18:30:42.176825Z"}},"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/sit
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"MSE: 1.3080\nR²:
6 0.7589\n","output_type":"stream"}],"execution_count":37},{"cell_type":"code","source":"\
17 LinearRegression()\nrandom_forest = RandomForestRegressor(n_estimators=300,
random_state=42)\nboosted_rf =
10 AdaBoostRegressor(base_estimator=RandomForestRegressor(n_estimators=100),
n_estimators=300, random_state=42)\ndecision_tree =
12 DecisionTreeRegressor(random_state=42)\nxgboost_model =
12 xgb.XGBRegressor(n_estimators=300, random_state=42)\ngradient_boosting =
GradientBoostingRegressor(n_estimators=300, random_state=42)\nsvr =
gradient_boosting),\n]\n\nmeta_model =
10 model\nstacking_regressor = StackingRegressor(estimators=base_models,
stacking_regressor.predict(X_test.drop('SMILES', axis=1))\nmse =
{mse:.4f}\")\nprint(f\"R²:
{r2:.4f}\")\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-
20T18:31:04.421922Z","iopub.execute_input":"2024-11-
20T18:31:04.422249Z","iopub.status.idle":"2024-11-
20T19:17:55.341302Z","shell.execute_reply.started":"2024-11-
20T18:31:04.422223Z","shell.execute_reply":"2024-11-
2 20T19:17:55.340338Z"}},"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/sit
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n/opt/conda/lib/python3.10/site-
warnings.warn(\n","output_type":"stream"},{"name":"stdout","text":"\nStacking
9 0.7607\n","output_type":"stream"}],"execution_count":38},{"cell_type":"code","source":"i
pd.read_csv('/kaggle/input/solublity/chi.csv')\n\n#
'InChIKey']\ndata = data.drop(columns=non_numeric_columns)\nlabel_encoder =
LabelEncoder()\ndata['Group'] = label_encoder.fit_transform(data['Group'])\n\nscaler =
10 xgb.XGBRegressor(n_estimators=100, learning_rate=0.1,
plot_type=\"bar\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-
11-24T13:48:04.046290Z","iopub.execute_input":"2024-11-
24T13:48:04.046881Z","iopub.status.idle":"2024-11-
24T13:48:13.464350Z","shell.execute_reply.started":"2024-11-
24T13:48:04.046805Z","shell.execute_reply":"2024-11-
2 24T13:48:13.463573Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<
Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAxYAAAOsCAYAAADX7yC0
AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM
6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAADq+U
lEQVR4nOzdeVTV1f7/8ddhUkQEZxGccEzIHI6iaThfk8Gch3JCc55yaLy3oux2r10zcyg
RZ82cygAH1HLKygFKSy2H0JzLCREVFTi/P/xxvh4PKPoBSXw+1mIt2Z/92Z/351Brndf
Ze3+OyWKxWAQAAAAABjjkdQEAAAAAHn0ECwAAAACGESwAAAAAGEawAAAAA
GAYwQIAAACAYQQLAAAAAIYRLAAAAAAYRrAAAAAAYBjBAgAAAIBhBAsgF82cOV
M3b97M6zIAAAByHcECAAAAgGEECwAAAACGESwAAAAAGEawAAAAAGAYwQIA
AACAYQQLAAAAAIYRLAAAAAAYRrAAAAAAYBjBAgAAAIBhBAsAAAAAhhEsAAAA
ABhGsAAAAABgGMECAAAAgGEECwAAAACGESwAAAAAGEawAAAAAGAYwQIAA
ACAYQQLAAAAAIYRLAAAAAAYRrAAAAAAYBjBAgAAAIBhBAsAAAAAhhEsAAAAA
BhGsAAAAABgGMECAAAAgGEECwAAAACGmSwWiyWviwDyK9PE1LwuAQAA5EO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SwWiyWviwDyK9PE1LwuATnEMs4pr0sAAOBvjRkLAAAAAIYRLAAAAAAYRrAAAAA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AIYRLAAAAAAYRrAAAAAAYBjBAgAAAIBhBAsAAAAAhhEsAAAAABhmslgslrwuAsiv
TBNT87qEvzXLOKe8LgEAAOQQZiwAAAAAGEawAAAAAGAYwQIAAACAYQQLAAA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GAYwQIAAACAYTzrEchFEUXmKCwsTM7OznldCgAAQK5ixgIAAACAYQQLAAAAAIY
RLAAAAAAYRrAAAAAAYBjBAgAAAIBhBAsAAAAAhhEsAAAAABhGsAAAAABgGME
CAAAAgGEECwAAAACGESwAAAAAGEawAAAAAGCYyWKxWPK6CCC/Mk1MzesS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EAAADAMIIFAAAAAMMIFgAAAAAMI1gAAAAAMIxgAQAAAMAwk8ViseR1EUB+ZZq
YmtclPBDLOKe8LgEAADximLEAAAAAYBjBAgAAAIBhBAsAAAAAhhEsAAAAABhGs
AAAAABgGMECAAAAgGEECwAAAACGESyQq0JDQzVw4MAHPn/gwIEKDQ3NwYo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ESwAAAAAGGayWCyWvC4CyK9ME1PzugQ7lnFOeV0CAADIh5ixAAAAAGAYwQIAA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AAAAAYRrAAAAAAYBjBAo+kgQMHKjQ0NK/LAAAAwP9HsECOiouLk9lsltls1oQJEzLt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AAAADCMYAEAAADAMIIFAAAAAMMIFgAAAAAMI1gAAAAAMIxgAQAAAMAwggUA
AAAAw0wWi8WS10UA+ZVpYmqeXNcyzilPrgsAAB5fzFgAAAAAMIxgAQAAAMAwggU
AAAAAwwgWAAAAAAwjWAAAAAAwjGABAAAAwDCCxWPIbDYrPDw8W31jYmJkNp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AAMN42D2QiyKKzFFYWJicnZ3zuhQAAIBcxYwFAAAAAMMIFgAAAAAMI1gAAAAAM
IxgAQAAAMAwggUAAAAAwwgWAAAAAAwjWAAAAAAwjGABAAAAwDCCBQAAAAD
DCBYAAAAADCNYAAAAADDMZLFYLHldBJBfmSam5vo1LOOccv0aAAAA98KMBQA
AAADDCBYAAAAADCNYAAAAADCMYAEAAADAMIIFAAAAAMMIFgAAAAAMI1gAA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DCNYAAAAADCMYAEAAADAMIIFAAAAAMMIFgAAAAAMI1gAAAAAMIxgAQAAAMA
wggUAAAAAw0wWi8WS10UA+ZVpYmqujm8Z55Sr4wMAAGQXMxYAAAAADCNYAA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1gAAAAAMIxgAQAAAMAwHoIP5KKIInMUFhYmZ2fnvC4FAAAgVzFjAQAAAMAwggU
AAAAAwwgWAAAAAAwjWAAAAAAwjGABAAAAwDCCBQAAAADDCBYAAAAADCN
YAAAAADCMYAEAAADAMIIFAAAAAMMIFgAAAAAMM1ksFkteFwHkV6aJqTk6nmW
cU46OBwAAkFOYsQAAAABgGMECAAAAgGEECwAAAACGESwAAAAAGEawAAAA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AAAAAMMIFgAAAAAMI1gAAAAAMIxgAQAAAMAwk8ViseR1EUB+ZZqY+sDnWsY55
WAlAAAAuYsZCwAAAACGESwAAAAAGEawAAAAAGAYwQIAAACAYQQLAAAAAIY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QIAAACAYQQLAAAAAIaZLBaLJa+LAPIr08TUBzrPMs4physBAADIXcxYAAAAADCM
YAEAAADAMIIFAAAAAMMIFgAAAAAMI1gAAAAAMIxgAQAAAMAwggUAAAAAwwg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sLC5OzsnNelAAAA5CpmLAAAAAAYRrAAAAAAYBjBAgAAAIBhBAsAAAAAhhEsAAA
AABhGsAAAAABgGMECAAAAgGEECwAAAACGESwAAAAAGEawAAAAAGAYwQIA
AACAYQQLAAAAAIaZLBaLJa+LAPIr08TUbPe1jHPKxUoAAAByFzMWAAAAAAwjWA
AAAAAwjGABAAAAwDCCBQAAAADDCBYAAAAADCNYAAAAADCMYAEAAADAsH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KmFgQEREREZHKmFgQEREREZHKmFgQEREREZHKmFgQEREREZHKRIIgCMUd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qY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBRERER
EQqY2JBREREREQqY2JBREREREQqY2JBREREREQqEwmCIBR3EEQ/KtHcbJm/h
XEaxRQJERERUdHiiAUREREREamMiQUREREREamMiQUREREREamMiQURERE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ilTGxICIiIiIilTGxICIiIiIil
TGxICIiIiIilTGxICIiIiIilYkEQRCKOwiiH5VobrbM38I4jWKKhIiIiKhoccSCiIiIiIhUxsSCiIiIiIh
UxsSCiIiIiIhUxsSCiIiIiIhUxsSCiIiIiIhUxsSCiIiIiIhUxsSCiIiIiIhUxsSCipy3tzcCAgJUaiM6O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OD
pqZmcYdCREREVKQ4YkFERERERCpjYkFERERERCpjYkFERERERCpjYkFERERE
RCpjYkFERERERCpjYkFERERERCpjYkFERERERCpjYkFERERERCpjYkFERERER
CpjYkFERERERCpjYkFERERERCpjYkFERERERCoTCYIgFHcQRD8q0dxs6f8L4zSK
MRIiIiKiosURCyIiIiIiUhkTCyIiIiIiUhkTCyIiIiIiUhkTCyIiIiIiUhkTCyIiIiIiUhkTCyIiIiIiUhkTCyq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kTCyIiIiIiU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hkTCy
IiIiIiUhkTCyIiIiIiUhkTC6IiFGq4Cu9GCrzVLBEREf3wmFgQEREREZHKmFgQEREREZ
HKmFgQEREREZHKmFgQEREREZHKmFgQEREREZHKmFgQEREREZHKmFgQER
EREZHKmFgQEREREZHKmFgQEREREZHKmFgQEREREZHKmFgQEREREZHKmF
gQEREREZHKmFgQFaGf0gYUdwhEREREXwUTCyIiIiIiUhkTCyIiIiIiUhkTCyIiIiIiUhkTC
yIiIiIiUhkTCyIiIiIiUhkTCyIiIiIiUhkTCyIiIiIiUplGcQdAJUNWVhZ27dqFw4cP4/bt20hPT4eu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SGV
MLIiIiIiISGVMLIiIiIiISGVMLIiKUKjhquIOgYiIiOirYGJBREREREQqY2JBREREREQqY2J
BREREREQqY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBREREREQqY
2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBREREREQ
qY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBRERER
EQqY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBREREREQqY2JBRER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REREREKmNiQUREREREKmNiQVSCvHjxAkZGRli+fLlMef/+/WFra1s8Qf0gAgMDIRK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RqYyJBRERERERqYyJBRERERERqez/AU+XdihybDR5AAAAAElFTkSuQmCC"},"met
3 adata":{}}],"execution_count":1},{"cell_type":"code","source":"import pandas as
'InChIKey']\ndata = data.drop(columns=non_numeric_columns)\nlabel_encoder =
LabelEncoder()\ndata['Group'] = label_encoder.fit_transform(data['Group'])\n\nscaler =
10 xgb.XGBRegressor(n_estimators=100, learning_rate=0.1,
11 explainer(X_test)\n\n# Save the mean absolute SHAP values for each feature to a
Importance'])\nfeature_importance.sort_values(by='SHAP Importance',
ascending=False, inplace=True)\nfeature_importance.to_csv('feature_importance.csv',
index=False)\n\n# Plotting the SHAP values with a scatter plot to show impact on
Plot')\nplt.bar(feature_importance['Feature'], feature_importance['SHAP
2 output)')\nplt.xticks(rotation=90)\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":t
rue,"execution":{"iopub.status.busy":"2024-11-
24T13:53:39.222541Z","iopub.execute_input":"2024-11-
24T13:53:39.222928Z","iopub.status.idle":"2024-11-
24T13:53:41.856308Z","shell.execute_reply.started":"2024-11-
24T13:53:39.222895Z","shell.execute_reply":"2024-11-
4 24T13:53:41.855429Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<
Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAwkAAAOsCAYAAAABSvrRA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e8DQEHQunIMSIgypFUoiv0Qt0mSIIQQQpi5/PIOQAjxyJEkQQghhBBCCGFAJiMKIYQ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RE
REYkwSSAiIiIiIhEmCUREREREJMIkgYiIiIiIRJgkEBERERGRCJMEIiIiIiISYZJARFTGD
R06FBKJRNdhAAD++ecfGBoaIiIiQl125MgRSCQSbNiwQXeBUZmwYcMGSCQSHDly
pEjv53dJu6ioKEilUhw9elTXodB7hEkCEenE3bt3MXr0aHh6esLMzAw2Njbw8vJCYGAg
IiMjRXXd3d3xwQcf5Lst1UV0XFyc1vXXr1+HRCKBRCLB8ePH892Oqo7qZWJigho1am
DKlCl4+fJl0Q5Uz0yZMgUtWrRAx44ddR1KqYiJicHMmTMRFRWl61ColCQmJmLmzJlF
TnSK6k3ftfr16yMgIACff/45BEEo1bjo/WWo6wCI6P1z4cIFtG7dGkZGRhgyZAhq166N9
PR03L59G+Hh4bCwsEDbtm2LbX9r166FhYUFTE1NsW7dOrRq1SrfuvXr18fnn38OAHj
58iX27duHRYsWISIiAhcvXoSxsXGxxVXenD59GhEREQgNDRWV+/r6Ij09HUZGRroJr
ATFxMRg1qxZcHd3R/369XUdDpWCxMREzJo1CwDQpk2bUtvv275rkyZNQuvWrbFv3
z5069at1OKi9xeTBCIqdbNmzUJaWhqioqJQr149jfVPnz4ttn1lZ2dj48aN6NOnD6ysrLB
q1SosXboUFhYWWutXrlwZgwYNUi9PmDABfn5+2LNnD3bv3o0+ffoUW2zlzYoVK2Bn
Z4euXbuKyqVSKUxMTHQUFdH7oVWrVnB3d8fKlSuZJFCpYHcjIip1t2/fhq2trdYEAQAc
HByKbV9//vknnj9/jsDAQAwdOhSpqanYtm1bobbRuXNnAMCdO3fyrfPrr79CIpEgLCxM
Y51SqYSzs7Po7mB4eDj69euHqlWrwtTUFNbW1ujUqVOB+xy3adMG7u7uGuUxMTG
QSCSYOXOmqFwQBPz6669o1KgRzMzMYG5ujrZt22p07cpPTk4OQkND0aFDB40W
A239yF8tW7FiBWrWrAkTExPUqVMHe/bsAQBcvXoVXbp0gaWlJWxtbTFhwgRkZ2drP
c67d++ie/fusLKygqWlJXr06IG7d++K6iqVSsyePRu+vr5wcHCAsbExXF1d8emnnyI+Pl7
rce3YsQNt2rSBtbU1zMzMULNmTUyYMAFZWVnYsGGDukVr2LBh6m5oBbm7HBMTg
8GDB6NSpUqQyWSoVq0aZsyYgbS0NFG9mTNnQiKR4ObNm5gxYwacnZ0hk8lQr14
97Nu37637Af4bB3Do0CF8//33cHNzg6mpKXx8fHDmzBkAwNGjR9GyZUvI5XI4Ojrif//7
n9ZthYaGokWLFpDL5TA3N0eLFi2we/durXVXr14NT09PyGQyVK9eHYsXL863K0xSU
hKmTZuG6tWrQyaTwd7eHv3799f4DAuroOf5TeN6JBIJhg4dCiDve1ulShUAeTczVJ+5
6rf26u/r999/R926dWFiYgJXV1fMnDkTOTk5om0X9HdakO+aRCJB586dceDAASgUikK
eKaLCY0sCEZW6atWq4ebNm9i5cyd69uxZoPfk5ubmO+YgMzMz3/etXbsWVapUQat
WrSCRSNCgQQOsW7cOI0eOLHC8t2/fBgDY2dnlW+fjjz/G5MmTERwcDH9/f9G6Q4c
O4dGjR+puTEDeRcHLly8xZMgQODs749GjR1izZg3at2+PyMjIN3aJKorBgwfj999/R+/e
vTFs2DBkZmZi8+bN6NixI3bu3KkR8+suXrwIhUKBJk2aFGq/y5cvR0JCAkaOHAkTExM
sXboUPXr0wB9//IFRo0ahf//+CAgIQHh4OJYtW4aKFSvi66+/Fm0jNTUVbdq0gY+PD+b
MmYPbt29jxYoVOHPmDC5fvqxOKrOysvDzzz+jV69e6N69O+RyOc6fP4+1a9fixIkTGt3
FvvrqK/z444+oVasWJk+eDEdHR0RHR2PHjh34/vvv4evrixkzZuDHH3/E6NGj1Z9JpUq
V3njM9+/fR5MmTZCUlISxY8eiRo0aOHLkCObMmYOTJ0/i0KFDMDQU//MbGBgIIyMjT
J06FVlZWVi8eDECAgJw69YtrReZ2kyfPh25ubmYOHEisrKysGDBAnTq1AnBwcEYM
WIERo8ejYEDB2L79u349ttvUaVKFVGr2YoVKzBu3Dh4enri22+/BZD3PQ0ICEBQUBB
Gjx6trrt48WJMnjwZ9erVw48//oi0tDTMnz8fFStW1IgrKSkJzZs3x4MHDzB8+HDUrl0bT5
48wYoVK+Dj44MLFy7Azc2tQMf4ruf5bby8vLBo0SJMnjwZPXr0UP99Mjc3F9ULCwvD3
bt3MW7cODg4OCAsLAyzZs3C/fv3sX79+kIfS0G/a82aNUNQUBBOnDiBLl26FHo/RIUi
EBGVslOnTglGRkYCAKFGjRrCsGHDhBUrVgjXrl3TWt/NzU0A8NbXixcvRO979OiRYG
BgIHz33XfqssWLFwsAtO4LgNCpUyfhxYsXwosXL4Rbt24JCxcuFIyMjAQrKyvh2bNnbz
yu3r17CzKZTHj58qWofNCgQYKhoaHo/QqFQuP9T58+FWxtbYUPP/xQVB4YGCi8/ue
6devWgpubm8Y27t27JwAQHfPOnTsFAEJQUJCobnZ2ttCoUSPB3d1dUCqVbzy2dev
WCQCE3bt3a6yLjIwUAAjr16/XKHNychISExPV5VeuXBEACBKJRNixY4doOw0bNhQc
HBw0jhOAMHHiRFG56pg++eQTdZlSqRTS0tI04luzZo0AQNi2bZu67OzZswIAoW3btkJ
6erqovlKpVJ8Pbcf2NgMGDBAACHv37hWVT506VQAgrFmzRl323XffCQCEbt26iT6Dc
+fOCQCE6dOnv3V/69evFwAIDRo0EDIzM9Xlu3fvFgAIhoaGwvnz59XlmZmZgoODg9C
0aVN12cuXLwW5XC5Uq1ZNSEpKUpcnJSUJVatWFczNzYWEhARBEAQhISFBMDMz
E7y8vITU1FR13djYWEEulwsAhMjISHX5hAkTBBMTEyEqKkoUd0xMjGBhYSEEBgaqy
wpzvgtznrX9hlQAiGLQ9ht6fZ1UKhUuXryoLlcqlUJAQIAAQDh9+rS6vDC/04Ic+/HjxwU
Awvz58/OtQ1Rc2N2IiEpds2bNcPHiRQQGBiIpKQnr16/H2LFjUatWLfj6+mrtguDu7o6IiA
itr06dOmndz4YNG6BUKjFkyBB12cCBA2FkZIR169ZpfU94eDjs7e1hb28PDw8PTJkyB
bVq1UJ4eLjWu6SvCgwMRGZmpqg7k0KhwK5du9ClSxfR++VyuahOfHw8DAwM4OPjg
7Nnz75xP4W1adMmWFhYICAgAHFxcepXYmIi/Pz8EBMTo24tyc+LFy8AABUqVCjUvo
cOHQorKyv1ct26dWFpaQknJyeNVqSWLVvi6dOnWrtSTJ8+XbTco0cP1KxZUzSIWiKR
wNTUFEBey1NiYiLi4uLQrl07ABCd182bNwMA5syZozGeQtXVoyiUSiXCwsLQoEEDjb
EbX375JaRSKXbt2qXxvokTJ4r22bhxY5ibm7/1c3nVp59+KmopUd2N9vHxgbe3t7rc2N
gYTZo0EW07IiICqampmDBhAiwtLdXllpaWmDBhAhQKBQ4ePAgg7zeSlpaGcePGwcz
MTF3X2dkZAwcOFMUkCAI2b94MX19fVK5cWfT9k8vlaNq0KcLDwwt8jCpFPc/FpWPH
jmjYsKF6WSKR4P/+7/8AoET3a2trCwB4/vx5ie2DSIXdjYhIJ+rUqaPuw37//n0cPXoUa9
aswfHjx9G9e3eNriFyuRwdOnTQuq1NmzZplAmCgHXr1qFu3bpQKpWi8QQtWrTAxo0
bMWfOHI3uCD4+Pvjhhx8AADKZDG5ubnB1dS3QMakSgeDgYIwZMwZAXp/31NRUU
aICANHR0fjqq6/w119/ITExUbSuuJ+JcP36daSkpLyxm8yzZ8/g4eGR73pVTEIhp1+sWr
WqRpmNjQ1cXFy0lgNAfHy8qHuHtbW11nEqXl5eCA0NRWpqqjrp2r59OxYsWIDLly9rj
G9ISEhQ///t27chkUjyHRdTVC9evIBCoUDt2rU11lWoUAGOjo5ak2Bt58nW1jbfsRTavL
4N1flU9bF/fd2r27537x4AaI1bVaaKW/VfT09Pjbq1atUSLb948QLx8fHq5FsbqbTw9yuLe
p6Li5eXl0aZ6thLcr+q319ZeW4K6TcmCUSkc25ubhgyZAgGDx6MVq1a4eTJkzh37hxat
mxZ5G0ePXoU0dHRAIAaNWporbNnzx4EBASIyuzs7PJNRt7G0NAQAwYMwOLFi3Hn
zh1Ur14dwcHBsLGxEfX5VygU8PX1RWpqKiZNmoQ6derAwsICUqkUc+bMweHDh9+6
r/wuEl4fOAnkXVjY29tjy5Yt+W7vTc+hAKC+wCvs8yIMDAwKVQ4UPhFR2blzJ/r164cm
TZpgyZIlcHFxgYmJCXJzc9GlSxcolUpR/XdpMShu+Z2PwpyLopzrkqaKv0OHDpg2bZr
O4ijM76Us71f1+8sv4SIqTkwSiKjMkEgk8PHxwcmTJ/Ho0aN32ta6desgk8kQHBys9U7l
J598grVr12okCe8qMDAQixcvRnBwMEaNGoUjR45g9OjRkMlk6jqHDh3C48ePsW7dO
gwbNkz0/tcH7eanQoUKuHjxoka5truYNWrUwK1bt9C0aVONAZgFpUoiCtP9pbgkJibi6d
OnGq0J169fR8WKFdWtCBs3boSJiQkiIyNF3WBu3LihsU0PDw/s378fV65ceeNg7MIm
Efb29rCwsMC///6rsS4hIQFPnjwpk89bULVC/Pvvv2jfvr1o3bVr10R1VP+9ceNGvnVV7O
3tYW1tjeTk5CIn39oU9jyrusm9fPlS1GVO2++lIJ/59evXNcpeP0+q/Rb0d1qQ/apaRN+W
1BMVB45JIKJSFxERofVOWnp6urp/8uvdFgojKSkJISEh6NSpE/r27YvevXtrvPz9/bF//3
48efKkyPvRpn79+qhbty42bdqEjRs3QqlUIjAwUFRHdWf39bvE4eHhBR6P4OHhgZSU
FJw7d05dplQqsWjRIo26Q4YMgVKpxJdffql1W8+ePXvr/ho0aABLS0v1lJql7aeffhIt79q1
Czdv3hQleQYGBpBIJKIWA0EQ1N3HXjVgwAAAwIwZM5CVlaWxXvXZqJKqgragSKV
S+Pn54fLlyzhw4IDGMSiVSvTo0aNA2ypNHTt2hFwux7Jly5CSkqIuT0lJwbJly2Bubq5+y
nbHjh1hamqK5cuXi6YaffjwoUZrlVQqxcCBA3Hu3DmEhIRo3XdR+tcX9jyrutKpxlWoLFi
wQGPbBfnMIyIicOnSJfWyIAiYN28eAIi+k4X5nRZkv2fOnIGhoSFatGiRbx2i4sKWBCIqd
ZMnT0Z8fDz8/f1Rp04dmJmZITY2Flu2bMGtW7cwZMgQ1KlTp8jb//3335Geno5evXrlW
6dXr17YsGEDfvvtN41Bse8qMDAQn3/+OebOnQsPDw80bdpUtL5ly5ZwcHDA559/jpiY
GDg7OyMqKgobN25EnTp1cPXq1bfuY/To0ViwYAF69OiBiRMnwtjYGCEhIVqTL9W0p
7/88gsuXbqEjz76CHZ2dnj48CFOnz6NO3fuvLUftYGBAXr27InQ0FBkZmaKWkZKmp2
dHXbu3InHjx+jTZs26ilQK1WqJHoeRO/evbFjxw60a9cOQ4YMQXZ2NkJDQzXmzAeAJ
k2aYNq0aZg7dy4aNmyIfv36wcHBAffu3UNISAjOnTsHa2tr1KpVCxYWFlixYgXMzMxgb
W2NihUrqgdDa/Pjjz8iIiICAQEBGDt2LKpXr45jx45h27Zt8PX11UgaywJra2vMmzcP48a
Ng4+Pj/q5ARs2bMCdO3cQFBSkHoBuY2OD//3vf5g6dSqaN2+OIUOGIC0tDStXrkSNG
jVw+fJl0bZnz56NkydPom/fvujbty+aNm0KY2Nj3L9/H/v27UOjRo1Ez9goqMKc5/79+2P
GjBkYPXo0bty4gQoVKuDAgQNap1W2tbVF9erVsXXrVlSrVg2VKlWCXC6Hn5+fuk69e
vXQrl07jBs3Do6Ojti9ezcOHjyIwYMHo1mzZup6hfmdvu27JggCDhw4gC5duhS5RZCo
UHQypxIRvdf++usvYezYsULdunUFW1tbwcDAQKhQoYLQpk0bYe3atUJubq6ovpubm
1C7du18t6ea3lA1Baq3t7dgaGioMRXpqzIyMgQLCwvBw8NDXYb/PxXlu3r69KlgaGgoA
BB++OEHrXWuXLkidO7cWbC2thbMzc2F1q1bC8eOHdM6VWN+0zfu3btXqFevnmBsb
Cw4OjoK//d//yfcuHEj3+kbg4ODhZYtWwoWFhaCTCYT3NzchB49eghbt24t0HGppg0N
CQkRlb9pClRt0zm6ubkJrVu31ihXTQd67949dZlqCsno6GjB399fsLCwEMzNzQV/f3/h9
u3bGttYtWqV4OXlJchkMsHBwUEYNWqUEB8frzHNpcqWLVuE5s2bC+bm5oKZmZlQs
2ZNYeLEiaKpRPfu3Ss0aNBAkMlkAgCtsb/u7t27wqBBgwR7e3vByMhIqFKlivDll1+Kpg
zN75jfdp5ep5oC9dVpR1XyO+78vlM7d+4UmjVrJpiZmQlmZmZCs2bNhF27dmnd78qV
KwUPDw/B2NhYqFatmrBo0SL1VLmvx5Kamip8//33wgcffCCYmJgI5ubmgqenpzBy5Ej
hzJkz6nqFnXK2oOdZEAThzJkzQvPmzQWZTCbY2toKo0aNEhISErSeo7NnzwrNmzcX
zMzMBADqaUxfnbp0y5YtQp06dQRjY2PB2dlZ+Oabb4SsrCyN/Rbmd/qm79qRI0cEAM
KePXsKdG6I3pVEEIo4QoyIiN47Xbp0QWpqKo4fP14q+2vTpg1iYmIQExNTKvsjepOY
mBhUqVIF3333ncZTzUtajx49EBsbi/Pnz5eZAfek3zgmgYiICmzBggU4ffp0kea2J6KiuXz
5Mnbv3o0FCxYwQaBSwzEJRERUYLVr1y7xaSOJSKxBgwYaU/gSlTS2JBARERERk
QjHJBARERERkQhbEoiIiIiISIRJAhERERERiTBJICIiIiIiESYJREREREQkwiSBiIiIiIhEm
CQQEREREZEIkwQiIiIiIhJhkkBERERERCJMEoiIiIiISOT/Abe0kSa4mgySAAAAAElFTk
4 SuQmCC"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure
Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAA90AAAJOCAYAAACqS2TfA
AAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6
Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAADFgklE
QVR4nOzdd3iN9//H8ddJSAQZZqyQqFFqU0pbrV2Uoq1Re1XV1ipaK9SoL2pLtQha66
uolhpNbWrP2oSo2iQxg+T+/eHn1JGEHN8c9znp83Fd57rcn3Ofc145knPO+3yWxTAM
QwAAAAAAINm5mR0AAAAAAICUiqIbAAAAAAAHoegGAAAAAMBBKLoBAAAAAHA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AwEEougEAAAAAcJB/5T7dcXFx+vvvv+Xt7W2zFykAAAAAAElhGIauX7+uHDlyyM0t8f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AAAAAB0ny8HIAcFWussq6q+QEAABA0tHTDQAAAACAg1B0AwAAAADgIBTdAAAA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ll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iIiIiIiqCYtuI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6CYiIiI
iIiKqJiy6iYiIiIiIiKoJi24iIiIiIiKiasKim4iIiIiIiKiasOgmIiIiIiIiqiYsuomIiIiIiIiqCYtuIiIiIiIiomrCopuIi
IiIiIiomrDoJiIiIiIiIqomLLqJiIiIiIiIqsn/AaZ2j9XZOAXFAAAAAElFTkSuQmCC"},"metadata"
2 :{}}],"execution_count":2},{"cell_type":"code","source":"","metadata":{"trusted":true},"out
puts":[],"execution_count":null}]}