1
2
3
4
5
6
pd_before = pd.DataFrame()
pd_before['new_x'] = new_x
pd_before['new_y'] = new_y
pd_before['new_plabel'] = new_plabel
pd_before['new_pinfo'] = new_pinfo

1
2
df_info_simple['drug'] = drug_new_list

1
2
3
df_drug_gene = pd.read_excel('../F1A-drug-go.xlsx', header = 0)
# header = 0 带列名数据

1
2
df_drug_gene = df_drug_gene[['drug', 'gene']]

1
2
df.iloc[:, n]

1
2
3
4
5
6
7
8
9
# 取第1行
print(df.iloc[0])
# 取前10行
print(df.iloc[:10])
# 取第1列
print(df.iloc[:, 0])
# 取前10列
print(df.iloc[:, :10])

1
2
pd_data_neg = pd_data.sample(n=pd_data_pos.shape[0])

1
2
pd_data_train = pd.concat([pd_data_pos, pd_data_neg])

1
2
3
for index, row in tqdm(df.iterrows(), total=df.shape[0]):
row[1] == 1

1
2
3
4
5
6
7
8
9
10
#满足条件的行
df.loc[df['A']=='A']
#也可以取满足条件范围的行
df.loc[df['B'] > 6]
data.iloc[:10,:]
# 存在某个字段
df[df['A'].isin(['A'])]
# 查找特定条件下的行索引
index = df[df.A == 'A'].index.tolist()[0]

1
2
3
pd_result_1 = pd.merge(df_drug_gene, df_symmap_info, left_on = 'gene',
right_on = 'Gene_symbol', how = 'left')

1
2
df_pw_Enrichment_result2.rename(columns={"go": "pw", "name": "pw_name"}, inplace=True)

1
2
dict_id_drug = df_drug.groupby('ID').drug.apply(list).to_dict()

1
2
3
4
5
6
7
df_new = pd_before.drop_duplicates(
subset = ['new_x', 'new_y'],
# 去重列，按这些列进行去重
keep = 'first'
# 保存第一条重复数据
)

1
2
df_book = df_book.dropna(subset=['content_id'])

1
2
pd_result_2.to_excel('../result/drug-gene.xlsx', index = False) # index = False 不保存列名

1
2
pd_result_2.to_csv('../result/drug-gene.csv', index = False, encoding='utf_8_sig')

1
2
3
4
import os
if not os.path.exists(save_path_dir):
os.makedirs(save_path_dir)