n = pd.Series(range(1,10))
n.apply(lambda r: "ID " + str(r))

f = pd.Series(["y","n","y","n","n"])
pd.factorize(f)
(array([0, 1, 0, 1, 1]), array(['y', 'n'], dtype=object))

pd.Series([True, False, True, True])

>>> r = pd.Series(range(11))
>>> l = r[r > 5]
>>> l.sum()
5
>>> l.any()
True

>>> l[l == True].index
Int64Index([6, 7, 8, 9, 10], dtype=int64)

>>> pd.Series([])
Series([], dtype: float64)

length(x) <- 10

>>> a = pd.Series(range(10))
>>> a[:5]
0    0
1    1
2    2
3    3
4    4
dtype: int64

>>> a = pd.Series(range(5), index=list("abcde"))
>>> a
a    0
b    1
c    2
d    3
e    4
dtype: int64
>>> a["c"]
2

>>> a = pd.Series(range(5), index=list("abcde"))
>>> a[list("ace")]
a    0
c    2
e    4
dtype: int64
>>> a[[0,2,4]]
a    0
c    2
e    4
dtype: int64
>>> a[(a<1)|(a>3)]
a    0
e    4
dtype: int64

>>> a = pd.Series(range(5))
>>> a[(a<1)|(a>3)].index
Int64Index([0, 4], dtype=int64)

>>> import numpy as np
>>> a = pd.Series(range(5))
>>> a.reindex(np.random.permutation(a.index))
2    2
0    0
3    3
1    1
4    4
dtype: int64
>>> b = a.reindex(np.random.permutation(a.index))
>>> b.sort()
>>> b
0    0
1    1
2    2
3    3
4    4
dtype: int64

>>> a = pd.Series(range(5))
>>> a
0    0
1    1
2    2
3    3
4    4
dtype: int64
>>> a[(a<1)|(a>3)] = 10
>>> a
0    10
1     1
2     2
3     3
4    10
dtype: int64

>>> a = pd.Series(range(5))
>>> a.append(pd.Series([0,0,0,0]))
0    0
1    1
2    2
3    3
4    4
0    0
1    0
2    0
3    0
dtype: int64

>>> a = pd.Series([1,2,3,4,5,4,6,3,2])
>>> a.duplicated()
0    False
1    False
2    False
3    False
4    False
5     True
6    False
7     True
8     True
dtype: bool
>>> a[a.duplicated()]
5    4
7    3
8    2
dtype: int64

>>> a.drop_duplicates()
0    1
1    2
2    3
3    4
4    5
6    6
dtype: int64

CHEMBL_URI=postgresql+psycopg2://localhost/chembl_17