2024-07-08
한어Русский языкEnglishFrançaisIndonesianSanskrit日本語DeutschPortuguêsΕλληνικάespañolItalianoSuomalainenLatina
# AI Summer Camp # Datawhale # Summer Camp
In addition to cross-validation, there is another key optimization method on the original baseline, namely feature engineering.
How to optimize features is related to improving the accuracy of model prediction. Feature engineering is often done by people who have a deep understanding of the problem domain, because we need to think about the way of conversion.
In addition to Smiles features, there are many other features that can be used to extract valuable information. For example, InChI is composed of a series of parts and provides detailed information about the molecular structure.Initial identifier, molecular formula, connection table, hydrogen atom count, multi-rotatable bond count, stereochemical information, isomer information, mixture or tautomer information, charge and spin multiplicity information, etc.
In addition, if you want to improve the accuracy of the model, changing the model is also a good idea.
From the InChI string, we can see that the molecular formula is given directly in/C47H61N7O6Spart. This means that the molecule is made up of 47 carbon atoms, 61 hydrogen atoms, 7 nitrogen atoms, 6 oxygen atoms, and 1 sulfur atom;
Molecular weight can be calculated by multiplying the atomic mass of each atom by the number of atoms and then adding the numbers.
like
The atomic mass of carbon (C) is about 12.01 g/mol
The atomic mass of hydrogen (H) is approximately 1.008 g/mol
The atomic mass of nitrogen (N) is approximately 14.01 g/mol
The atomic mass of oxygen (O) is approximately 16.00 g/mol
The atomic mass of sulfur (S) is approximately 32.07 g/mol
Multiplying by adding the quantities, we get the molecular weight.
Directly calculate the number of different atoms and expand them.
import pandas as pd
import re
atomic_masses = {
'H': 1.008, 'He': 4.002602, 'Li': 6.94, 'Be': 9.0122, 'B': 10.81, 'C': 12.01,
'N': 14.01, 'O': 16.00, 'F': 19.00, 'Ne': 20.180, 'Na': 22.990, 'Mg': 24.305,
'Al': 26.982, 'Si': 28.085, 'P': 30.97, 'S': 32.07, 'Cl': 35.45, 'Ar': 39.95,
'K': 39.10, 'Ca': 40.08, 'Sc': 44.956, 'Ti': 47.867, 'V': 50.942, 'Cr': 52.00,
'Mn': 54.938, 'Fe': 55.845, 'Co': 58.933, 'Ni': 58.69, 'Cu': 63.55, 'Zn': 65.38
}
# 函数用于解析单个InChI字符串
def parse_inchi(row):
inchi_str = row['InChI']
formula = ''
molecular_weight = 0
element_counts = {}
# 提取分子式
formula_match = re.search(r"InChI=1S/([^/] )/c", inchi_str)
if formula_match:
formula = formula_match.group(1)
# 计算分子量和原子计数
for element, count in re.findall(r"([A-Z][a-z]*)([0-9]*)", formula):
count = int(count) if count else 1
element_mass = atomic_masses.get(element.upper(), 0)
molecular_weight = element_mass * count
element_counts[element.upper()] = count
return pd.Series({
'Formula': formula,
'MolecularWeight': molecular_weight,
'ElementCounts': element_counts
})
# 应用函数到DataFrame的每一行
train[['Formula', 'MolecularWeight', 'ElementCounts']] = train.apply(parse_inchi, axis=1)
# 定义存在的key
keys = ['H', 'He', 'Li', 'Be', 'B', 'C', 'N', 'O', 'F', 'Ne', 'Na', 'Mg', 'Al', 'Si', 'P', 'S', 'Cl', 'Ar', 'K', 'Ca', 'Sc', 'Ti', 'V', 'Cr', 'Mn', 'Fe', 'Co', 'Ni', 'Cu', 'Zn']
# 创建一个空的DataFrame，列名为keys
df_expanded = pd.DataFrame({key: pd.Series() for key in keys})
# 遍历数据，填充DataFrame
for index, item in enumerate(train['ElementCounts'].values):
for key in keys:
# 将字典中的值填充到相应的列中
df_expanded.at[index, key] = item.get(key, 0)
df_expanded = pd.DataFrame(df_expanded)
Last time I mentioned that we used the catboost model and had not tried lightgbm and xgboost. We can run these three models in turn and then average the results of the three models for fusion (which is also an area that can be improved).
def cv_model(clf, train_x, train_y, test_x, clf_name, seed = 2023):
folds = 5
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
oof = np.zeros(train_x.shape[0])
test_predict = np.zeros(test_x.shape[0])
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(train_x, train_y)):
print('************************************ {} ************************************'.format(str(i 1)))
trn_x, trn_y, val_x, val_y = train_x.iloc[train_index], train_y[train_index], train_x.iloc[valid_index], train_y[valid_index]
if clf_name == "lgb":
train_matrix = clf.Dataset(trn_x, label=trn_y)
valid_matrix = clf.Dataset(val_x, label=val_y)
params = {
'boosting_type': 'gbdt',
'objective': 'binary',
'min_child_weight': 6,
'num_leaves': 2 ** 6,
'lambda_l2': 10,
'feature_fraction': 0.8,
'bagging_fraction': 0.8,
'bagging_freq': 4,
'learning_rate': 0.35,
'seed': 2024,
'nthread' : 16,
'verbose' : -1,
}
model = clf.train(params, train_matrix, 2000, valid_sets=[train_matrix, valid_matrix],
categorical_feature=[], verbose_eval=1000, early_stopping_rounds=100)
val_pred = model.predict(val_x, num_iteration=model.best_iteration)
test_pred = model.predict(test_x, num_iteration=model.best_iteration)
if clf_name == "xgb":
xgb_params = {
'booster': 'gbtree',
'objective': 'binary:logistic',
'num_class':3,
'max_depth': 5,
'lambda': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'eta': 0.35,
'tree_method': 'hist',
'seed': 520,
'nthread': 16
}
train_matrix = clf.DMatrix(trn_x , label=trn_y)
valid_matrix = clf.DMatrix(val_x , label=val_y)
test_matrix = clf.DMatrix(test_x)
watchlist = [(train_matrix, 'train'),(valid_matrix, 'eval')]
model = clf.train(xgb_params, train_matrix, num_boost_round=2000, evals=watchlist, verbose_eval=1000, early_stopping_rounds=100)
val_pred = model.predict(valid_matrix)
test_pred = model.predict(test_matrix)
if clf_name == "cat":
params = {'learning_rate': 0.35, 'depth': 5, 'bootstrap_type':'Bernoulli','random_seed':2024,
'od_type': 'Iter', 'od_wait': 100, 'random_seed': 11, 'allow_writing_files': False}
model = clf(iterations=2000, **params)
model.fit(trn_x, trn_y, eval_set=(val_x, val_y),
metric_period=1000,
use_best_model=True,
cat_features=[],
verbose=1)
val_pred = model.predict_proba(val_x)
test_pred = model.predict_proba(test_x)
oof[valid_index] = val_pred
test_predict = test_pred / kf.n_splits
F1_score = f1_score(val_y, np.where(val_pred
个人简介
潜心研究技术三十余年，精通java、linux、javascript、php、css、等等各种语言，在开源领域有诸多贡献，建立开发者文档站，将一些技术开发中的问题分享出来，以供大家查阅
我的联系方式