ronakmutha

>>> import pandas as pd
>>> import numpy as np
>>> series = pd.Series([12,32,54,2, np.nan, "a string", 6])
>>> series
0          12
1          32
2          54
3           2
4         NaN
5    a string

ronakmutha

>>> series = pd.Series([1,2,np.nan, 4])
>>> series
0    1.0
1    2.0
2    NaN
3    4.0
dtype: float64

ronakmutha

>>> d = {
    "stats": pd.Series(np.arange(10,15,1.0)),
    "year": pd.Series(["2012","2007","2012","2003"]),
    "intake": pd.Series(["SUMMER","WINTER","WINTER","SUMMER"]),
}
>>> df = pd.DataFrame(d)
>>> df

ronakmutha

>>> import pandas as pd
>>> nrows, ncols = 100000, 100
>>> rng = np.random.RandomState(42)
>>> df1, df2, df3, df4 = (pd.DataFrame(rng.rand(nrows, ncols))
                      for i in range(4))

ronakmutha

>>> %timeit df1 + df2 + df3 + df4

10 loops, best of 3: 103.1 ms per loop

ronakmutha

>>> %timeit pd.eval('df1 + df2 + df3 + df4')

10 loops, best of 3: 53.6 ms per loop

ronakmutha

>>> np.allclose(df1 + df2 + df3 + df4,d.eval('df1 + df2 + df3 + df4'))

True

ronakmutha

>>> df = pd.read_csv('companies.csv')
>>> df.head()

ronakmutha

>>> %timeit df.query("vertical == 'B2B' and year == 2009")

875 µs ± 24.6 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

ronakmutha

>>> %timeit df[(df['vertical'] == 'B2B') & (df['year'] == 2009)]

1.69 ms ± 57 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)