papers_dates[(papers_dates.preprint_test == True) & ~ papers_dates.acptDate.isna()]
# 两列做 or 运算
df_all_norm[(df_all_norm["CO2"] > 0.8) | (df_all_norm["CO"] > 0.8)]

papers_age[papers_age.pubDate >= "2028-03-01"]

papers_dates[papers_dates.preprint_age > pd.Timedelta(30,'D')]

df.dropna(subset=['name', 'toy'])

pd.concat([papers, CSCoV_scores], axis=1)

papers_redup.merge(all_rxiv_redup[['subDate', 'title']], left_on='title', right_on='title',how='left')

df.replace([0, 1, 2, 3], [4, 3, 2, 1])

pd.set_option('display.max_colwidth', None)

X_lxd[X_lxd.title.isin(selected)][['title', 'pub_prob']]

papers_dates[['subDate', 'acptDate', 'pubDate']].describe(datetime_is_numeric=True)

X_lxd.sort_values(by='pub_prob', ascending=False)

x = np.random.rand(3,1)
1 + x # element-wise operation
1 - x
1 * x
1 / x

x = np.zeros((10, 1))
x = np.ones((10, 1))

x = np.random.rand(3,1)
x.mean()
x.std()
x.max()
x.min()
np.median(x)

x = np.random.rand(3,1)
y = np.random.rand(3,1)
np.maximum(x, y) # also np.maximum(x, 0) broadcast by default
# Out: array([[0.88240057], [0.38776741], [0.72610557]])

x = np.random.rand(3,1)
y = np.random.rand(3,1)
x * y # element-wise multiplication, return vector (3,1), or np.multiply()
np.transpose(x).dot(y) # return scalar
x / y # element-wise division, return vector (3,1)

np.absolute(np.random.rand(3, 2，2)-10)

x = np.random.rand(3, 2，2)
x.shape   # (3, 2，2)
x.reshape(-1, 1) # a column vector, 1 f

# reshape a np.array of images
train_set_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T