Pandas Exercises for Data Analysis (Continuously updated)

location

# 1. How to import pandas and check the version?
import pandas as pd

print(pd.__version__)
print(pd.show_versions(as_json=True))

0.23.4
{'system': {'commit': None, 'python': '3.7.0.final.0', 'python-bits': 64, 'OS': 'Windows', 'OS-release': '10', 'machine': 'AMD64', 'processor': 'Intel64 Family 6 Model 142 Stepping 10, GenuineIntel', 'byteorder': 'little', 'LC_ALL': 'None', 'LANG': 'None', 'LOCALE': 'None.None'}, 'dependencies': {'pandas': '0.23.4', 'pytest': '3.8.0', 'pip': '19.2.1', 'setuptools': '40.2.0', 'Cython': '0.28.5', 'numpy': '1.17.2', 'scipy': '1.1.0', 'pyarrow': None, 'xarray': None, 'IPython': '6.5.0', 'sphinx': '1.7.9', 'patsy': '0.5.0', 'dateutil': '2.7.3', 'pytz': '2018.5', 'blosc': None, 'bottleneck': '1.2.1', 'tables': '3.4.4', 'numexpr': '2.6.8', 'feather': None, 'matplotlib': '2.2.3', 'openpyxl': '2.5.6', 'xlrd': '1.1.0', 'xlwt': '1.3.0', 'xlsxwriter': '1.1.0', 'lxml': '4.2.5', 'bs4': '4.6.3', 'html5lib': '1.0.1', 'sqlalchemy': '1.2.11', 'pymysql': None, 'psycopg2': None, 'jinja2': '2.10', 's3fs': None, 'fastparquet': None, 'pandas_gbq': None, 'pandas_datareader': None}}
None

# 2. How to create a series from a list, numpy array and dict?
import numpy as np
mylist = list('abcedfghijklmnopqrstuvwxyz')
myarr = np.arange(26)
mydict = dict(zip(mylist, myarr))

# ser1 = pd.Series(mylist)
# ser2 = pd.Series(myarr)
ser3 = pd.Series(mydict)
print(ser3.head(3))

a    0
b    1
c    2
dtype: int64

# 3. How to convert the index of a series into a column of a dataframe?
mylist = list('abcedfghijklmnopqrstuvwxyz')
myarr = np.arange(26)
mydict = dict(zip(mylist, myarr))
ser = pd.Series(mydict)
ser.describe()

df = ser.to_frame().reset_index()
print(df.head())

  index  0
0     a  0
1     b  1
2     c  2
3     e  3
4     d  4

# 4. How to combine many series to form a dataframe?
import numpy as np
ser1 = pd.Series(list('abcedfghijklmnopqrstuvwxyz'))
ser2 = pd.Series(np.arange(26))

# Solution 1
df = pd.concat([ser1, ser2], axis=1)

# Solution 2
# df = pd.DataFrame({'col1':ser1, 'col2': ser2})
print(df.head())

   0  1
0  a  0
1  b  1
2  c  2
3  e  3
4  d  4

# 5. How to assign name to the series’ index?
# Give a name to the series ser calling it ‘alphabets’.
ser = pd.Series(list('abcedfghijklmnopqrstuvwxyz'))

ser.name = 'alphabets'
ser.head()

0    a
1    b
2    c
3    e
4    d
Name: alphabets, dtype: object

# 6. How to get the items of series A not present in series B?
# From ser1 remove items present in ser2.
ser1 = pd.Series([1, 2, 3, 4, 5])
ser2 = pd.Series([4, 5, 6, 7, 8])
# print(ser1.isin(ser2))
ser1[~ser1.isin(ser2)]

0    1
1    2
2    3
dtype: int64

# 7. How to get the items not common to both series A and series B?
# Get all items of ser1 and ser2 not common to both.
ser1 = pd.Series([1, 2, 3, 4, 5])
ser2 = pd.Series([4, 5, 6, 7, 8])

ser_u = pd.Series(np.union1d(ser1, ser2))
ser_i = pd.Series(np.intersect1d(ser1, ser2))
ser_u[~ser_u.isin(ser_i)]

0    1
1    2
2    3
5    6
6    7
7    8
dtype: int64

# 8. How to get the minimum, 25th percentile, median, 75th, and max of a numeric series?
# Compute the minimum, 25th percentile, median, 75th, and maximum of ser.
ser = pd.Series(np.random.normal(10, 5, 25))

np.percentile(ser, q=[0, 25, 50, 75, 100])

array([ 1.6294664 ,  6.63669818,  9.88911315, 12.63793738, 19.94314505])

# 9. How to get frequency counts of unique items of a series?
# Calculte the frequency counts of each unique value ser.
ser = pd.Series(np.take(list('abcdefgh'), np.random.randint(8, size=30)))

ser.value_counts()

c    6
h    6
b    4
f    4
g    4
a    3
e    2
d    1
dtype: int64

# 10. How to keep only top 2 most frequent values as it is and replace everything else as ‘Other’?
# From ser, keep the top 2 most frequent items as it is and replace everything else as ‘Other’.
np.random.RandomState(100)
ser = pd.Series(np.random.randint(1, 5, [12]))

print("Top 2 Freq:", ser.value_counts())
ser[~ser.isin(ser.value_counts().index[:2])] = 'Other'
ser

Top 2 Freq: 3    5
2    3
4    2
1    2
dtype: int64





0         3
1         2
2     Other
3         2
4     Other
5         3
6         2
7     Other
8     Other
9         3
10        3
11        3
dtype: object

# 11. How to bin a numeric series to 10 groups of equal size?
# Bin the series ser into 10 equal deciles and replace the values with the bin name.
# Input
ser = pd.Series(np.random.random(20))
print(ser.head())

# Solution
pd.qcut(ser, q=[0, .10, .20, .3, .4, .5, .6, .7, .8, .9, 1], 
        labels=['1st', '2nd', '3rd', '4th', '5th', '6th', '7th', '8th', '9th', '10th']).head()

0    0.733123
1    0.512086
2    0.325354
3    0.634904
4    0.802665
dtype: float64





0    8th
1    5th
2    3rd
3    7th
4    9th
dtype: category
Categories (10, object): [1st < 2nd < 3rd < 4th ... 7th < 8th < 9th < 10th]

# 12. How to convert a numpy array to a dataframe of given shape? 
# Reshape the series ser into a dataframe with 7 rows and 5 columns
ser = pd.Series(np.random.randint(1, 10, 35))
pd.DataFrame(ser.values.reshape(7, 5))

# 13. How to find the positions of numbers that are multiples of 3 from a series?
# Find the positions of numbers that are multiples of 3 from ser.
ser = pd.Series(np.random.randint(1, 10, 7))

print(ser)
np.argwhere(ser % 3 == 0)

0    8
1    9
2    5
3    8
4    6
5    7
6    7
dtype: int32





array([[1],
       [4]], dtype=int64)

# 14. How to extract items at given positions from a series
# From ser, extract the items at positions in list pos.
ser = pd.Series(list('abcdefghijklmnopqrstuvwxyz'))
pos = [0, 4, 8, 14, 20]

# ser[pos]
ser.take(pos)

0     a
4     e
8     i
14    o
20    u
dtype: object

# 15. How to stack two series vertically and horizontally ?
# Stack ser1 and ser2 vertically and horizontally (to form a dataframe).
ser1 = pd.Series(range(5))
ser2 = pd.Series(list('abcde'))

# Vertical
ser1.append(ser2)

# Horizontal
df = pd.concat([ser1, ser2], axis=1)
print(df)

   0  1
0  0  a
1  1  b
2  2  c
3  3  d
4  4  e

# 16. How to get the positions of items of series A in another series B?
# Get the positions of items of ser2 in ser1 as a list.
ser1 = pd.Series([10, 9, 6, 5, 3, 1, 12, 8, 13])
ser2 = pd.Series([1, 3, 10, 13])

# Solution 1
[np.where(i == ser1)[0].tolist()[0] for i in ser2]

# Solution 2
[pd.Index(ser1).get_loc(i) for i in ser2]

[5, 4, 0, 8]

# 17. How to compute the mean squared error on a truth and predicted series?
# Compute the mean squared error of truth and pred series.

原文地址：https://www.cnblogs.com/ohou/p/11933928.html