- import pandas as pd
- import numpy as np
- from tqdm.auto import tqdm
- from rdkit import Chem
- from rdkit.Chem import rdMolDescriptors #molecular descriptors
- from lightgbm import LGBMRegressor, plot_importance #LightGBM models
- from sklearn.model_selection import train_test_split #ML trainining
- from sklearn.metrics import r2_score, mean_squared_error #ML stats
- import seaborn as sns #Plotting
- from yellowbrick.regressor import prediction_error, ResidualsPlot
-
- sns.set_context('talk')
- tqdm.pandas()
- df = pd.read_csv("solubility_data_ok.csv")
- df.head()
property_name