Table of Contents |
---|
Get last name from full name by split()
The function can be easily implemented by string method
Basic Data Types
Constant values by the types
Value | Python Expression |
---|---|
Hexa decimal a1 | 0xa1 |
3.2e-12 | |
|
|
String
String concatenation by join()
Write the code for a Python function expand(x) that takes a list of strings, concatenates them, and returns the resulting string repeated three times.
Info |
---|
|
Code Block |
---|
def expand(x |
Code Block |
actor = {"name": "John Cleese", "rank": "awesome"} def get_last_name(): return actor["name"].split()[1] get_last_name() print("All exceptions caught! Good job!") print("The actor's last name is %s" % get_last_name()) |
Create a Pandas DataFrame based on array
Code Block |
---|
dict = {"country": ["Brazil", "Russia", "India", "China", "South Africa"],
"capital": ["Brasilia", "Moscow", "New Dehli", "Beijing", "Pretoria"],
"area": [8.516, 17.10, 3.286, 9.597, 1.221],
"population": [200.4, 143.5, 1252, 1357, 52.98] }
import pandas as pd
brics = pd.DataFrame(dict)
print(brics) |
Adding index to DataFrame
Code Block |
---|
# Set the index for brics
brics.index = ["BR", "RU", "IN", "CH", "SA"]
# Print out brics with new index values
print(brics) |
Reading CSV by Pandas DataFrame
Code Block |
---|
# Import pandas as pd
import pandas as pd
# Import the cars.csv data: cars
cars = pd.read_csv('cars.csv')
# Print out cars
print(cars) |
Reading a CSV file by Pandas DataFrame with 1st column as index
Code Block |
---|
# Import pandas and cars.csv
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out country column as Pandas Series
print(cars['cars_per_cap'])
# Print out country column as Pandas DataFrame
print(cars[['cars_per_cap']])
# Print out DataFrame with country and drives_right columns
print(cars[['cars_per_cap', 'country']]) |
Save a Pandas DaraFrame by CSV format
Code Block |
---|
dict = {"country": ["Brazil", "Russia", "India", "China", "South Africa"],
"capital": ["Brasilia", "Moscow", "New Dehli", "Beijing", "Pretoria"],
"area": [8.516, 17.10, 3.286, 9.597, 1.221],
"population": [200.4, 143.5, 1252, 1357, 52.98] }
import pandas as pd
brics = pd.DataFrame(dict)
brics.to_csv('example.csv') |
Save a Pandas DaraFrame by CSV format with header and no index
Code Block |
---|
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000]
}
df = DataFrame(Cars, columns= ['Brand', 'Price'])
export_csv = df.to_csv (r'C:\Users\Ron\Desktop\export_dataframe.csv', index = None, header=True) #Don't forget to add '.csv' at the end of the path
print (df) |
Print partial rows (observations) from a Pandas DataFrame
Code Block |
---|
# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out first 4 observations
print(cars[0:4])
# Print out fifth, sixth, and seventh observation
print(cars[4:6]) |
Data access by loc and iloc in Pandas DaraFrame
loc is label-based, and iloc is integer index based
Code Block |
---|
# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out observation for Japan
print(cars.iloc[2])
# Print out observations for Australia and Egypt
print(cars.loc[['AUS', 'EG']]) |
Sort a Pandas DataFrame in an ascending order
Info |
---|
df.sort_values(by=['Brand'], inplace=True) |
Code Block |
---|
# sort - ascending order
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000],
'Year': [2015,2013,2018,2018]
}
df = DataFrame(Cars, columns= ['Brand', 'Price','Year'])
# sort Brand - ascending order
df.sort_values(by=['Brand'], inplace=True)
print (df) |
Sort a Pandas DataFrame in a descending order
Info |
---|
df.sort_values(by=['Brand'], inplace=True, ascending=False) |
Code Block |
---|
# sort - descending order
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000],
'Year': [2015,2013,2018,2018]
}
df = DataFrame(Cars, columns= ['Brand', 'Price','Year'])
# sort Brand - descending order
df.sort_values(by=['Brand'], inplace=True, ascending=False)
print (df) |
Sort a Pandas DataFrame by multiple columns
Info |
---|
df.sort_values(by=['First Column','Second Column',...], inplace=True) |
Code Block |
---|
# sort by multiple columns
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000],
'Year': [2015,2013,2018,2018]
}
df = DataFrame(Cars, columns= ['Brand', 'Price','Year'])
# sort by multiple columns: Year and Price
df.sort_values(by=['Year','Price'], inplace=True)
print (df) |
Random number generation
Code Block |
---|
import random
def lottery():
# returns 6 numbers between 1 and 40
for i in range(6):
yield random.randint(1, 40)
# returns a 7th number between 1 and 15
yield random.randint(1,15)
for random_number in lottery():
print("And the next number is... %d!" %(random_number)) |
Swap variables' value
Code Block |
---|
a = 1
b = 2
a, b = b, a
print(a,b) |
Fibonacci series generator
The first two numbers of the series is always equal to 1, and each consecutive number returned is the sum of the last two numbers - the below code uses only two variables to get the result.
Code Block |
---|
def fib():
a, b = 1, 1
while 1:
yield a
a, b = b, a + b
# testing code
import types
if type(fib()) == types.GeneratorType:
print("Good, The fib function is a generator.")
counter = 0
for n in fib():
print(n)
counter += 1
if counter == 10:
break |
Split string as list
Code Block |
---|
sentence = "the quick brown fox jumps over the lazy dog"
words = sentence.split()
print(words) |
Filter positive numbers only - 1
Code Block |
---|
numbers = [34.6, -203.4, 44.9, 68.3, -12.2, 44.6, 12.7]
newlist = []
for number in numbers:
if number>0:
newlist.append(number)
print(newlist) |
Filter positive numbers only - 2
Code Block |
---|
numbers = [34.6, -203.4, 44.9, 68.3, -12.2, 44.6, 12.7]
newlist = [int(x) for x in numbers if x > 0]
print(newlist) |
Multiple Function Argument recognition - the list of "therest" parameters
Code Block |
---|
def foo(first, second, third, *therest):
print("First: %s" %(first))
print("Second: %s" %(second))
print("Third: %s" %(third))
print("And all the rest... %s" %(list(therest)))
foo(1,2,3,4,5) |
Multiple Function Argument by keyword
Code Block |
---|
def bar(first, second, third, **options):
if options.get("action") == "sum":
print("The sum is: %d" %(first + second + third))
if options.get("number") == "first":
return first
result = bar(1, 2, 3, action = "sum", number = "first")
print("Result: %d" %(result)) |
RegEx(Regular Expressions) to search "[on]" or "[off]" on the string
Code Block |
---|
import re
pattern = re.compile(r"\[(on|off)\]") # Slight optimization
print(re.search(pattern, "Mono: Playback 65 [75%] [-16.50dB] [on]")) |
RegEx(Regular Expression) to check email address
Code Block |
---|
import re
def test_email(your_pattern):
pattern = re.compile(your_pattern)
emails = ["john@example.com", "python-list@python.org", "wha.t.`1an?ug{}ly@email.com"]
for email in emails:
if not re.match(pattern, email):
print("You failed to match %s" % (email))
elif not your_pattern:
print("Forgot to enter a pattern!")
else:
print("Pass")
pattern = r"[a-z0-9]+@[a-z0-9]+\.[a-z0-9]+"
test_email(pattern) |
Exception Handling - try/except block
Code Block |
---|
def do_stuff_with_number(n):
print(n)
def catch_this():
the_list = (1, 2, 3, 4, 5)
for i in range(20):
try:
do_stuff_with_number(the_list[i])
except IndexError: # Raised when accessing a non-existing index of a list
do_stuff_with_number('out of bound - %d' % i)
catch_this()
|
Create word list from a sentence with no duplicate entries
set() removes all the duplicate entries in the array
Code Block |
---|
strings = "my name is Chun Kang and Chun is my name"
r = set(strings.split())
print(r) |
Find overlapped entries from two arrays
Code Block |
---|
a = set([ "Seoul", "Pusan", "Incheon", "Mokpo" ])
b = set([ "Seoul", "Incheon", "Suwon", "Daejeon", "Gwangjoo", "Taeku"])
print(a.intersection(b))
print(b.intersection(a)) |
The result will be like below
...
{'Seoul', 'Incheon'}
{'Seoul', 'Incheon'}
Find different elements from two arrays based on "symmetric_difference" method
Code Block |
---|
a = set(["Jake", "John", "Eric"])
b = set(["John", "Jill"])
print(a.symmetric_difference(b))
print(b.symmetric_difference(a)) |
The result will be like below
...
{'Jake', 'Eric', 'Jill'}
{'Eric', 'Jake', 'Jill'}
Find different elements from two arrays based on "difference" method
Code Block |
---|
a = set(["Jake", "John", "Eric"])
b = set(["John", "Jill"])
print(a.difference(b))
print(b.difference(a)) |
The result will be like below
...
{'Jake', 'Eric'}
{'Jill'}
Find different elements from two arrays based on "union" method
Code Block |
---|
a = set(["Jake", "John", "Eric"])
b = set(["John", "Jill"])
print(a.union(b)) |
The result will be like below
...
{'John', 'Eric', 'Jake', 'Jill'}
''.join(x) * 3 |
Print string n times
Code Block |
---|
n = 2;
s ="Programming";
print(s * n); # ProgrammingProgramming |
Basic Operators
Python Arithmetic Operators
Operator | Description | Example |
---|---|---|
+ Addition | Adds values on either side of the operator. | 10 + 20 = 30 |
- Subtraction | Subtracts right hand operand from left hand operand. | 10 – 20 = -10 |
* Multiplication | Multiplies values on either side of the operator | 10 * 20 = 200 |
/ Division | Divides left hand operand by right hand operand | 20 / 10 = 2 |
% Modulus | Divides left hand operand by right hand operand and returns remainder | 20 % 10 = 0 |
** Exponent | Performs exponential (power) calculation on operators | 10**20 =10 to the power 20 |
// | Floor Division - The division of operands where the result is the quotient in which the digits after the decimal point are removed. But if one of the operands is negative, the result is floored, i.e., rounded away from zero (towards negative infinity) − | 9//2 = 4 and 9.0//2.0 = 4.0 -11//3 = -4 -11.0//3 = -4.0 |
Python Comparison Operators
Info |
---|
Below example is based on the condition as a=10, b=20 |
Operator | Description | Example |
---|---|---|
== | If the values of two operands are equal, then the condition becomes true. | (a == b) is not true. |
!= | If values of two operands are not equal, then condition becomes true. | (a != b) is true. |
<> | If values of two operands are not equal, then condition becomes true. | (a <> b) is true. This is similar to != operator. |
> | If the value of left operand is greater than the value of right operand, then condition becomes true. | (a > b) is not true. |
< | If the value of left operand is less than the value of right operand, then condition becomes true. | (a < b) is true. |
>= | If the value of left operand is greater than or equal to the value of right operand, then condition becomes true. | (a >= b) is not true. |
<= | If the value of left operand is less than or equal to the value of right operand, then condition becomes true. | (a <= b) is true. |
Data Structures - List / Set / Tuple / Dictionary
List
Code Block |
---|
list1 = ['physics', 'chemistry', 1997, 2000];
list2 = [1, 2, 3, 4, 5 ];
list3 = ["a", "b", "c", "d"] |
Split string as list
Code Block |
---|
sentence = "the quick brown fox jumps over the lazy dog"
words = sentence.split()
print(words) |
Filter positive numbers only - 1
Code Block |
---|
numbers = [34.6, -203.4, 44.9, 68.3, -12.2, 44.6, 12.7]
newlist = []
for number in numbers:
if number>0:
newlist.append(number)
print(newlist) |
Filter positive numbers only - 2
Code Block |
---|
numbers = [34.6, -203.4, 44.9, 68.3, -12.2, 44.6, 12.7]
newlist = [int(x) for x in numbers if x > 0]
print(newlist) |
Create word list from a sentence with no duplicate entries
set() removes all the duplicate entries in the array
Code Block |
---|
strings = "my name is Chun Kang and Chun is my name"
r = set(strings.split())
print(r) |
Python List REPL sessions
Code Block |
---|
a = ['foo', 'bar', 'baz', 'qux', 'quux', 'corge']
print(a[:] is a)
print(max(a[2:4] + ['grault']))
print(a[-5:-3])
print(a[-6])
print(a[4::-2]) |
Diagram for the list indices:
'foo' | 'bar' | 'baz' | 'qux' | 'quux' | 'corge' |
---|---|---|---|---|---|
0 | 1 | 2 | 3 | 4 | 5 |
-6 | -5 | -4 | -3 | -2 | -1 |
Result
Code Block |
---|
False
qux
['bar', 'baz']
foo
['quux', 'baz', 'foo'] |
Delete element in Python List
Code Block |
---|
a = [1, 2, 3, 4, 5]
# option 1 - delete element 3
del a[2]
# option 2 - delete element 3
a.remove(3)
# option 3 - delete element 3
a[2:3] = [] |
Tuple
Info |
---|
The tuples cannot be changed unlike lists and tuples use parentheses, whereas lists use square brackets. |
Code Block |
---|
tup1 = ('physics', 'chemistry', 1997, 2000);
tup2 = (1, 2, 3, 4, 5 );
tup3 = "a", "b", "c", "d"; |
Ascending sort
Code Block |
---|
# set
pySet = {'e', 'a', 'u', 'o', 'i'}
print(sorted(pySet))
# dictionary
pyDict = {'e': 1, 'a': 2, 'u': 3, 'o': 4, 'i': 5}
print(sorted(pyDict))
# tuple
pyTuple = ('e', 'a', 'u', 'o', 'i')
print(sorted(pyTuple)) |
Descending sort
Code Block |
---|
# set
pySet = {'e', 'a', 'u', 'o', 'i'}
print(sorted(pySet, reverse=True))
# dictionary
pyDict = {'e': 1, 'a': 2, 'u': 3, 'o': 4, 'i': 5}
print(sorted(pyDict, reverse=True))
# tuple
pyTuple= ('e', 'a', 'u', 'o', 'i')
print(sorted(pyTuple, reverse=True)) |
Set
Info |
---|
Unordered collections of unique elements |
Code Block |
---|
Set(['Jane', 'Marvin', 'Janice', 'John', 'Jack'])
Set(['Janice', 'Jack', 'Sam'])
Set(['Jane', 'Zack', 'Jack'])
Set(['Jack', 'Sam', 'Jane', 'Marvin', 'Janice', 'John', 'Zack']) |
Implement the unique_names by combining two lists
The returned list should have no duplicates and it must be sorted.
Code Block |
---|
def unique_names(names1, names2):
names1 += names2
return sorted( set(names1))
names1 = ["Ava", "Emma", "Olivia"]
names2 = ["Olivia", "Sophia", "Emma"]
print(unique_names(names1, names2)) # should print Ava, Emma, Olivia, Sophia |
Find overlapped entries from two arrays
Code Block |
---|
a = set([ "Seoul", "Pusan", "Incheon", "Mokpo" ])
b = set([ "Seoul", "Incheon", "Suwon", "Daejeon", "Gwangjoo", "Taeku"])
print(a.intersection(b))
print(b.intersection(a)) |
The result will be like below
Result |
---|
{'Seoul', 'Incheon'} {'Seoul', 'Incheon'} |
Find different elements from two arrays based on "symmetric_difference" method
Code Block |
---|
a = set(["Jake", "John", "Eric"])
b = set(["John", "Jill"])
print(a.symmetric_difference(b))
print(b.symmetric_difference(a)) |
The result will be like below
Result |
---|
{'Jake', 'Eric', 'Jill'} {'Eric', 'Jake', 'Jill'} |
Find different elements from two arrays based on "difference" method
Code Block |
---|
a = set(["Jake", "John", "Eric"])
b = set(["John", "Jill"])
print(a.difference(b))
print(b.difference(a)) |
The result will be like below
Result |
---|
{'Jake', 'Eric'} {'Jill'} |
Find different elements from two arrays based on "union" method
Code Block |
---|
a = set(["Jake", "John", "Eric"])
b = set(["John", "Jill"])
print(a.union(b)) |
The result will be like below
Result |
---|
{'John', 'Eric', 'Jake', 'Jill'} |
Print out a set containing all the participants from event A which did not attend event B
Code Block |
---|
a = ["Jake", "John", "Eric"]
b = ["John", "Jill"]
print(set(a).difference(set(b))) |
Find sorted unique names in two list
Code Block |
---|
def unique_names(names1, names2):
return sorted(set(names1+names2))
names1 = ["Ava", "Emma", "Olivia"]
names2 = ["Olivia", "Sophia", "Emma"]
print(unique_names(names1, names2)) # should print Ava, Emma, Olivia, Sophia |
Dictionary
Info |
---|
Python dictionaries are similar to lists in that they are mutable and can be nested to any arbitrary depth (constrained only by available memory). A dictionary can contain any type of Python object, including another dictionary. The keys in a given dictionary do not need to be the same type as one another, nor do the values. Dictionary elements are accessed by key. Unlike with list indexing, the order of the items in a dictionary plays no role in how the items are accessed. Even though dictionary access does not rely on item order, as of version 3.7 the Python language specification does guarantee that the order of items in a dictionary is maintained once the dictionary is created. |
Code Block |
---|
dict = {'Name': 'Zara', 'Age': 7, 'Class': 'First'} |
Get last name from full name by split()
The function can be easily implemented by string method
Code Block |
---|
actor = {"name": "John Cleese", "rank": "awesome"}
def get_last_name():
return actor["name"].split()[1]
get_last_name()
print("All exceptions caught! Good job!")
print("The actor's last name is %s" % get_last_name()) |
Accessing dictionary values
Code Block |
---|
x = [
'a',
'b',
{
'foo': 1,
'bar':
{
'x' : 10,
'y' : 20,
'z' : 30
},
'baz': 3
},
'c',
'd'
]
print(x[2]['bar']['z']) |
Result
Code Block |
---|
30 |
Delete a dictionary element
Deleting a dictionary element by statement
Code Block |
---|
del d['foo'] |
Deleting a dictionary element by method
Code Block |
---|
d.pop('foo') |
Copying a dictionary
Method 1)
Code Block |
---|
d2 = dict(d1) |
Method 2)
Code Block |
---|
d2 = dict(d1.items()) |
Method 3)
Code Block |
---|
d2 = {}
d2.update(d1) |
Hashmap
Python kindly provides a built-in type hashmap named as dictionary. You can easily hash like below:
Code Block |
---|
myHashmap = {}
# hash by name
myHashmap['Chun'] = 1234
myHashmap['John'] = 2342
# print hash value
print( myHashmap['Chun']) |
Generator
Random number generation
Code Block |
---|
import random
def lottery():
# returns 6 numbers between 1 and 40
for i in range(6):
yield random.randint(1, 40)
# returns a 7th number between 1 and 15
yield random.randint(1,15)
for random_number in lottery():
print("And the next number is... %d!" %(random_number)) |
Swap variables' value
Code Block |
---|
a = 1
b = 2
a, b = b, a
print(a,b) |
Fibonacci series generator
The first two numbers of the series is always equal to 1, and each consecutive number returned is the sum of the last two numbers - the below code uses only two variables to get the result.
Code Block | ||
---|---|---|
| ||
def fib():
a, b = 1, 1
while 1:
yield a
a, b = b, a + b
# testing code
import types
if type(fib()) == types.GeneratorType:
print("Good, The fib function is a generator.")
counter = 0
for n in fib():
print(n)
counter += 1
if counter == 10:
break |
Function Arguments(Parameters)
Multiple Function Argument recognition - the list of "therest" parameters
Code Block |
---|
def foo(first, second, third, *therest):
print("First: %s" %(first))
print("Second: %s" %(second))
print("Third: %s" %(third))
print("And all the rest... %s" %(list(therest)))
foo(1,2,3,4,5) |
Multiple Function Argument by keyword
Code Block |
---|
def bar(first, second, third, **options):
if options.get("action") == "sum":
print("The sum is: %d" %(first + second + third))
if options.get("number") == "first":
return first
result = bar(1, 2, 3, action = "sum", number = "first")
print("Result: %d" %(result)) |
Regular Expression
RegEx(Regular Expressions) to search "[on]" or "[off]" on the string
Code Block | ||
---|---|---|
| ||
import re
pattern = re.compile(r"\[(on|off)\]") # Slight optimization
print(re.search(pattern, "Mono: Playback 65 [75%] [-16.50dB] [on]")) |
RegEx(Regular Expression) to check email address
Code Block | ||
---|---|---|
| ||
import re
def test_email(your_pattern):
pattern = re.compile(your_pattern)
emails = ["john@example.com", "python-list@python.org", "wha.t.`1an?ug{}ly@email.com"]
for email in emails:
if not re.match(pattern, email):
print("You failed to match %s" % (email))
elif not your_pattern:
print("Forgot to enter a pattern!")
else:
print("Pass")
pattern = r"[a-z0-9]+@[a-z0-9]+\.[a-z0-9]+"
test_email(pattern) |
Exception Handling
try/except block
Code Block | ||
---|---|---|
| ||
def do_stuff_with_number(n):
print(n)
def catch_this():
the_list = (1, 2, 3, 4, 5)
for i in range(20):
try:
do_stuff_with_number(the_list[i])
except IndexError: # Raised when accessing a non-existing index of a list
do_stuff_with_number('out of bound - %d' % i)
catch_this()
|
Numpy
Convert arrays to Numpy arrays
Code Block | ||
---|---|---|
| ||
# Create 2 new lists height and weight
height = [1.87, 1.87, 1.82, 1.91, 1.90, 1.85]
weight = [81.65, 97.52, 95.25, 92.98, 86.18, 88.45]
# Import the numpy package as np
import numpy as np
# Create 2 numpy arrays from height and weight
np_height = np.array(height)
np_weight = np.array(weight)
print(type(np_height))
# Calculate bmi
bmi = np_weight / np_height ** 2
# Print the result
print(bmi)
# For a boolean response
print(bmi > 23)
# Print only those observations above 23
print(bmi[bmi > 23]) |
Result
Code Block |
---|
<class 'numpy.ndarray'>
[ 23.34925219 27.88755755 28.75558507 25.48723993 23.87257618
25.84368152]
[ True True True True True True]
[ 23.34925219 27.88755755 28.75558507 25.48723993 23.87257618
25.84368152] |
Convert all of the weights from kilograms to pounds based in NumPy
Code Block |
---|
weight_kg = [81.65, 97.52, 95.25, 92.98, 86.18, 88.45]
import numpy as np
# Create a numpy array np_weight_kg from weight_kg
np_weight_kg = np.array(weight_kg)
# Create np_weight_lbs from np_weight_kg
np_weight_lbs = np_weight_kg * 2.2
# Print out np_weight_lbs
print(np_weight_lbs) |
Result
Code Block |
---|
[ 179.63 214.544 209.55 204.556 189.596 194.59 ] |
Pandas DataFrame / CSV / Join / Merge
Create a Pandas DataFrame based on array
Code Block |
---|
dict = {"country": ["Brazil", "Russia", "India", "China", "South Africa"],
"capital": ["Brasilia", "Moscow", "New Dehli", "Beijing", "Pretoria"],
"area": [8.516, 17.10, 3.286, 9.597, 1.221],
"population": [200.4, 143.5, 1252, 1357, 52.98] }
import pandas as pd
brics = pd.DataFrame(dict)
print(brics) |
Adding index to a Pandas DataFrame
Code Block |
---|
# Set the index for brics
brics.index = ["BR", "RU", "IN", "CH", "SA"]
# Print out brics with new index values
print(brics) |
Reading CSV by Pandas DataFrame
Code Block |
---|
# Import pandas as pd
import pandas as pd
# Import the cars.csv data: cars
cars = pd.read_csv('cars.csv')
# Print out cars
print(cars) |
CSV
Reading a CSV file by Pandas DataFrame with 1st column as index
Code Block |
---|
# Import pandas and cars.csv
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out country column as Pandas Series
print(cars['cars_per_cap'])
# Print out country column as Pandas DataFrame
print(cars[['cars_per_cap']])
# Print out DataFrame with country and drives_right columns
print(cars[['cars_per_cap', 'country']]) |
Save a Pandas DaraFrame by CSV format
Code Block |
---|
dict = {"country": ["Brazil", "Russia", "India", "China", "South Africa"],
"capital": ["Brasilia", "Moscow", "New Dehli", "Beijing", "Pretoria"],
"area": [8.516, 17.10, 3.286, 9.597, 1.221],
"population": [200.4, 143.5, 1252, 1357, 52.98] }
import pandas as pd
brics = pd.DataFrame(dict)
brics.to_csv('example.csv') |
Save a Pandas DaraFrame by CSV format with header and no index
Code Block |
---|
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000]
}
df = DataFrame(Cars, columns= ['Brand', 'Price'])
export_csv = df.to_csv (r'C:\Users\Ron\Desktop\export_dataframe.csv', index = None, header=True) #Don't forget to add '.csv' at the end of the path
print (df) |
Print partial rows (observations) from a Pandas DataFrame
Code Block |
---|
# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out first 4 observations
print(cars[0:4])
# Print out fifth, sixth, and seventh observation
print(cars[4:6]) |
Data access by loc and iloc in Pandas DaraFrame - Select colums by index or name
loc is label-based, and iloc is integer index based
Code Block |
---|
# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out observation for Japan
print(cars.iloc[2])
# Print out observations for Australia and Egypt
print(cars.loc[['AUS', 'EG']]) |
Sort
Sort a Pandas DataFrame in an ascending order
Info |
---|
df.sort_values(by=['Brand'], inplace=True) |
Code Block |
---|
# sort - ascending order
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000],
'Year': [2015,2013,2018,2018]
}
df = DataFrame(Cars, columns= ['Brand', 'Price','Year'])
# sort Brand - ascending order
df.sort_values(by=['Brand'], inplace=True)
print (df) |
Sort a Pandas DataFrame in a descending order
Info |
---|
df.sort_values(by=['Brand'], inplace=True, ascending=False) |
Code Block |
---|
# sort - descending order
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000],
'Year': [2015,2013,2018,2018]
}
df = DataFrame(Cars, columns= ['Brand', 'Price','Year'])
# sort Brand - descending order
df.sort_values(by=['Brand'], inplace=True, ascending=False)
print (df) |
Sort a Pandas DataFrame by multiple columns
Info |
---|
df.sort_values(by=['First Column','Second Column',...], inplace=True) |
Code Block |
---|
# sort by multiple columns
from pandas import DataFrame
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
'Price': [22000,25000,27000,35000],
'Year': [2015,2013,2018,2018]
}
df = DataFrame(Cars, columns= ['Brand', 'Price','Year'])
# sort by multiple columns: Year and Price
df.sort_values(by=['Year','Price'], inplace=True)
print (df) |
Join and merge Pandas DataFrames
Code Block |
---|
import pandas as pd
from IPython.display import display
from IPython.display import Image
raw_data = {
'subject_id': ['1', '2', '3', '4', '5'],
'first_name': ['Alex', 'Amy', 'Allen', 'Alice', 'Ayoung'],
'last_name': ['Anderson', 'Ackerman', 'Ali', 'Aoni', 'Atiches']}
df_a = pd.DataFrame(raw_data, columns = ['subject_id', 'first_name', 'last_name'])
raw_data = {
'subject_id': ['4', '5', '6', '7', '8'],
'first_name': ['Billy', 'Brian', 'Bran', 'Bryce', 'Betty'],
'last_name': ['Bonder', 'Black', 'Balwner', 'Brice', 'Btisan']}
df_b = pd.DataFrame(raw_data, columns = ['subject_id', 'first_name', 'last_name'])
raw_data = {
'subject_id': ['1', '2', '3', '4', '5', '7', '8', '9', '10', '11'],
'test_id': [51, 15, 15, 61, 16, 14, 15, 1, 61, 16]}
df_n = pd.DataFrame(raw_data, columns = ['subject_id','test_id'])
# Join the two dataframes along rows
df_new = pd.concat([df_a, df_b])
# Join the two dataframes along columns
pd.concat([df_a, df_b], axis=1)
# Merge two dataframes along the subject_id value
pd.merge(df_new, df_n, on='subject_id')
# Merge two dataframes with both the left and right dataframes using the subject_id key
pd.merge(df_new, df_n, left_on='subject_id', right_on='subject_id')
# Merge with outer join
pd.merge(df_a, df_b, on='subject_id', how='outer')
# Merge with inner join
pd.merge(df_a, df_b, on='subject_id', how='inner')
# Merge with right join
pd.merge(df_a, df_b, on='subject_id', how='right')
# Merge with left join
pd.merge(df_a, df_b, on='subject_id', how='left')
# Merge while adding a suffix to duplicate column names
pd.merge(df_a, df_b, on='subject_id', how='left', suffixes=('_left', '_right'))
# Merge based on indexes
pd.merge(df_a, df_b, right_index=True, left_index=True) |
Get the maximum value of column in Pandas DataFrame
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]
}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# get the maximum values of all the column in dataframe - it will be raghu, 26, 89, object
df.max()
# get the maximum value of the column 'Age' - it will be 26
df['Age'].max()
# get the maximum value of the column 'Name' - it will be raghu
df['Name'].max() |
Get the minimum value of column in Pandas DataFrame
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]
}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# get the minimum values of all the column in dataframe - it will display Alex, 22, 31, object
df.min()
# get the minimum value of the column 'Age' - it will be 22
df['Age'].min()
# get the minimum value of the column 'Name' - it will be Alex
df['Name'].min() |
Select row with maximum and minimum value in Pandas DataFrame
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# get the row of max value
df.loc[df['Score'].idxmax()]
# get the row of minimum value
df.loc[df['Score'].idxmin()] |
Get the unique values (rows) of a Pandas Dataframe
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24]
}
df = pd.DataFrame(d,columns=['Name','Age'])
# get the unique values (rows)
print df.drop_duplicates()
# get the unique values (rows) by retaining last row
print df.drop_duplicates(keep='last') |
Get the list of column headers or column name in a Pandas DataFrame
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# method 1: get list of column name
list(df.columns.values)
# method 2: get list of column name
list(df) |
Delete or Drop the duplicate row of a Pandas DataFrame
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# drop duplicate rows
df.drop_duplicates()
# drop duplicate rows by retaining last occurrence
df.drop_duplicates(keep='last')
# drop duplicate by a column name
df.drop_duplicates(['Name'], keep='last') |
Drop or delete the row in Pandas DataFrame with conditions
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
# Drop an observation or row
df.drop([1,2])
# Drop a row by condition
df[df.Name != 'Alisa']
# Drop a row by index
df.drop(df.index[2])
# Drop bottom 3 rows
df[:-3] |
Reshape wide to long in Pandas DataFrame with melt() function
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'countries':['A','B','C'],
'population_in_million':[100,200,120],
'gdp_percapita':[2000,7000,15000]
}
df = pd.DataFrame(d,columns=['countries','population_in_million','gdp_percapita'])
# shape from wide to long with melt function in pandas
df2=pd.melt(df,id_vars=['countries'],var_name='metrics', value_name='values') |
Reshape long to wide in Pandas DataFrame with pivot function
Code Block |
---|
import pandas as pd
# Create a DataFrame
d = {
'countries':['A','B','C','A','B','C'],
'metrics':['population_in_million','population_in_million','population_in_million',
'gdp_percapita','gdp_percapita','gdp_percapita'],
'values':[100,200,120,2000,7000,15000]
}
df = pd.DataFrame(d,columns=['countries','metrics','values'])
# reshape from long to wide in pandas python
df2=df.pivot(index='countries', columns='metrics', values='values')
|
Reshape using Stack() and unstack() function in Pandas DataFrame
Code Block |
---|
import pandas as pd
header = pd.MultiIndex.from_product([['Semester1','Semester2'],['Maths','Science']])
d=([[12,45,67,56],[78,89,45,67],[45,67,89,90],[67,44,56,55]])
df = pd.DataFrame(d,
index=['Alisa','Bobby','Cathrine','Jack'],
columns=header)
# stack the dataframe
stacked_df=df.stack()
# unstack the dataframe
unstacked_df = stacked_df.unstack()
# stack the dataframe of column at level 0
stacked_df_lvl=df.stack(level=0)
# unstack the dataframe
unstacked_df1 = stacked_df_lvl.unstack() |
MatPlotLib
Line chart by city and population by MatPlotLib
Code Block |
---|
from matplotlib import pyplot as plt
plt.plot(["Seoul","Paris","Seattle"], [30,25,55])
plt.xlabel('City')
plt.ylabel('Response')
plt.title('Experiment Result')
plt.show() |
Result
Bar chart by city and population by MatPlotLib
Code Block |
---|
from matplotlib import pyplot as plt
plt.bar(["Seoul","Paris","Seattle"], [30,25,55])
plt.xlabel('City')
plt.ylabel('Response')
plt.title('Experiment Result')
plt.show() |
Result
Spot graph by age and score by MapPlotLib
Below code shows a graph displaying multiple spots by age and score stored in a pandas data frame.
Code Block | ||
---|---|---|
| ||
import pandas as pd
from matplotlib import pyplot as plt
# Create a DataFrame
d = {
'Name':['Alisa','Bobby','jodha','jack','raghu','Cathrine',
'Alisa','Bobby','kumar','Alisa','Alex','Cathrine'],
'Age':[26,24,23,22,23,24,26,24,22,23,24,24],
'Score':[85,63,55,74,31,77,85,63,42,62,89,77]
}
df = pd.DataFrame(d,columns=['Name','Age','Score'])
plt.plot(df['Age'], df['Score'], 'ro')
plt.xlabel('Age')
plt.ylabel('Score')
plt.title('Experiment Result')
plt.show() |
Result
Draw Samsung's stock price by MatPlotLib
Code Block |
---|
import matplotlib
matplotlib.use('Agg')
import pandas as pd
import matplotlib
matplotlib.use('Agg')
from matplotlib import pyplot as plt
import os
samsung = pd.read_csv('http://qsok.com/test/py/005930.csv')
# samsung.set_index( 'Date', inplace=True)
print("<pre>")
print(samsung)
print("\n")
max_date = samsung['Date'].max()
print('Last date of record stored %s' % max_date)
print("</pre>")
if not os.path.exists('./samsung_stock_price.png'):
plt.plot(samsung['Date'], samsung['Close'])
plt.xlabel('Date')
plt.ylabel('Close')
plt.title('Experiment Result')
plt.savefig('samsung_stock_price.png')
print("<img src=samsung_stock_price.png>")
|
Result
...
OS
Check if file exists or not
Code Block |
---|
import os
if not os.path.exists('test.png'):
# do something if 'test.png' does not exist
pass
|
Algorithms
Check all unique or not
Code Block |
---|
def all_unique(lst):
return len(lst) == len(set(lst))
x = [1,1,2,2,3,2,3,4,5,6]
y = [1,2,3,4,5]
all_unique(x) # False
all_unique(y) # True |
Palindrome number - Determine whether an integer is a palindrome
Code Block |
---|
def is_palindrome(word):
j = len(word)-1
i =0
while i<j and word[i].lower()==word[j].lower():
i+=1
j-=1
return (i>=j)
print(is_palindrome('Deleveled')) |
Two sum - return indices of the two numbers such that they add up to a specific target
Info |
---|
Given nums = [2, 7, 11, 15], target = 9, Because nums[0] + nums[1] = 2 + 7 = 9, |
Code Block |
---|
def twoSum(self, nums, target):
seen = {}
for i, v in enumerate(nums):
remaining = target - v
if remaining in seen:
return [seen[remaining], i]
seen[v] = i
return [] |
Reverse integer - Given a 32-bit signed integer, reverse digits of an integer.
Info |
---|
Input: 123 → Output: 321 |
Code Block |
---|
class Solution(object):
def reverse(self, x):
if x >= 2**31-1 or x <= -2**31:
return 0
else:
strg = str(x)
if x >= 0 :
revst = strg[::-1]
else:
temp = strg[1:]
temp2 = temp[::-1]
revst = "-" + temp2
if int(revst) >= 2**31-1 or int(revst) <= -2**31:
return 0
else:
return int(revst) |
Merge two sorted linked lists and return it as a new list.
Info |
---|
Input: 1->2->4, 1->3->4 |
Code Block | ||
---|---|---|
| ||
class Solution:
def mergeTwoLists(self, l1, l2):
result = ListNode(0) # The new list we are going to eventually return
head = result # keep a pointer to the head so we can return head.next in the end
while(l1 != None and l2 != None): # This check is important in the case where one list is shorter than the other
if l1.val < l2.val: # Add l1's value as a new node to result if its less than l2's
result.next = ListNode(l1.val)
l1 = l1.next
result = result.next
elif l2.val < l1.val: # Add l2's value as a new node to result if its less than l1's
result.next = ListNode(l2.val)
l2 = l2.next
result = result.next
else: # In this case, the values must be equal so add both to result and move the linked lists forward
result.next = ListNode(l1.val)
result = result.next
result.next = ListNode(l2.val)
result = result.next
l1 = l1.next
l2 = l2.next
if l1 == None and l2 != None: # If l2 is longer than l1, add all of the remaining values of l2 to result
while(l2 != None):
result.next = ListNode(l2.val)
result = result.next
l2 = l2.next
elif l2 == None and l1 != None: # if l1 is longer than l2, add all of the remaining values of l1 to result
while(l1 != None):
result.next = ListNode(l1.val)
result = result.next
l1 = l1.next
return head.next # return the result |
Remove Duplicates from Sorted Array
Code Block | ||
---|---|---|
| ||
class Solution(object):
def removeDuplicates(self, nums):
if not nums:
return 0
i = 1
bound = len(nums)
prev = nums[0]
while i < bound:
if prev == nums[i]:
nums.pop(i)
bound = len(nums)
else:
prev = nums[i]
i += 1
return len(nums) |
Longest common prefix
Info |
---|
Input: ["flower", "flow", "flight" ] → Output: "fl" Input: ["dog", "racecar", "car"] → Output: "" |
Code Block | ||
---|---|---|
| ||
class Solution:
def longestCommonPrefix(self, strs: List[str]) -> str:
if not strs:
return ""
result=""
cnt=len(strs)
for i in range(len(strs[0])):
j=1
while j<cnt and i<len(strs[j]) and strs[j][i]==strs[0][i]: j+=1
if j==cnt:
result += strs[0][i]
else:
break;
return result; |
Longest Palindromic Substring
Info |
---|
Input: "babad" → Output: "bab" Input: "cbd" → Output: "bb" |
Code Block |
---|
class Solution:
def longestPalindrome(self, s):
"""
:type s: str
:rtype: str
"""
# Return if string is empty
if not s: return s
res = ""
for i in range(len(s)):
j = i + 1
# While j is less than length of string
# AND res is *not* longer than substring s[i:]
while j <= len(s) and len(res) <= len(s[i:]):
# If substring s[i:j] is a palindrome
# AND substring is longer than res
if s[i:j] == s[i:j][::-1] and len(s[i:j]) > len(res):
res = s[i:j]
j += 1
return res |
Same Tree
Code Block | ||
---|---|---|
| ||
# Definition for a binary tree node.
# class TreeNode:
# def __init__(self, x):
# self.val = x
# self.left = None
# self.right = None
class Solution:
def isSameTree(self, p: TreeNode, q: TreeNode) -> bool:
if p==None and q!=None: return False
if p!=None and q==None: return False
if p==None and q==None: return True
if p.val==q.val:
return self.isSameTree(p.left, q.left) and self.isSameTree(p.right, q.right) |
Merge Sorted Array
Info |
---|
Given two sorted integer arrays nums1 and nums2, merge nums2 into nums1 as one sorted array. nums1 = [1,2,3,0,0,0], m = 3 Output: [1,2,2,3,5,6] |
Code Block | ||
---|---|---|
| ||
class Solution:
def merge(self, nums1: List[int], m: int, nums2: List[int], n: int) -> None:
"""
Do not return anything, modify nums1 in-place instead.
"""
p = m+n-1
m -= 1
n -= 1
while p>=0:
if n<0:
break;
elif m<0:
nums1[p] = nums2[n]
n-=1
elif nums1[m]<nums2[n]:
nums1[p] = nums2[n]
n-=1
else:
nums1[p] = nums1[m]
m-=1
p-=1 |
Minimum Depth of Binary Tree
Info |
---|
Given binary tree [3,9,20,null,null,15,7], 3 |
Code Block | ||
---|---|---|
| ||
# Definition for a binary tree node.
# class TreeNode:
# def __init__(self, x):
# self.val = x
# self.left = None
# self.right = None
class Solution:
def minDepth(self, root: TreeNode) -> int:
if root==None:
return 0
if root.left==None and root.right==None: return 1
elif root.left!=None and root.right!=None:
return min( self.minDepth(root.left), self.minDepth(root.right)) + 1
elif root.left==None:
return self.minDepth(root.right) + 1
else:
return self.minDepth(root.left) + 1
|
Reorder List
Info |
---|
Given a singly linked list L: L0→L1→…→Ln-1→Ln, ex1) Given 1->2->3->4, reorder it to 1->4->2->3. |
Code Block | ||
---|---|---|
| ||
# Definition for singly-linked list.
# class ListNode:
# def __init__(self, x):
# self.val = x
# self.next = None
class Solution:
def reorderList(self, head: ListNode) -> None:
"""
Do not return anything, modify head in-place instead.
"""
# collect value serially
v=[]
p=head
while p!=None:
v.append(p.val)
p=p.next
# reorder based on the given logic
i=0
lcnt=len(v)
j=lcnt-1
p=head
while p!=None:
p.val = v[i]
i += 1
p=p.next
if p!=None:
p.val = v[j]
j-=1
p = p.next
|
Compact - Remove Falsy values (None, False, "")
Code Block |
---|
def compact(lst):
return list(filter(None, lst))
compact([0, 1, False, 2, '', 3, 'a', 's', 34]) # [ 1, 2, 3, 'a', 's', 34 ] |
Python Simple Web Server
Code Block | ||||
---|---|---|---|---|
| ||||
import SimpleHTTPServer
import SocketServer
PORT = 8888
Handler = SimpleHTTPServer.SimpleHTTPRequestHandler
httpd = SocketServer.TCPServer(("", PORT), Handler)
print "serving at port", PORT
httpd.serve_forever() |
You can run above as
Code Block |
---|
python -m simple_http_server.py |
Print out a set containing all the participants from event A which did not attend event B
Code Block |
---|
a = ["Jake", "John", "Eric"]
b = ["John", "Jill"]
print(set(a).difference(set(b))) |