PYTHON PYTHON PYTHON¶
Python for DataScience¶
In [1]:
print('Hello')
$a=b+c$ (did it using $ symbols at the end)
Variables¶
In [1]:
x = 3
In [2]:
%whos
In [3]:
print(type(x))
In [4]:
x = 5.07
In [5]:
%whos
In [6]:
print(type(x))
In [7]:
num = 234
In [8]:
%whos
In [9]:
a,b,c = 34,23.234,-23
In [11]:
whos
In [12]:
del num
In [13]:
%whos
In [14]:
c = 2+4j
In [15]:
print(type(c))
In [16]:
word = "HELLOOO"
In [17]:
print(type(word))
Operators¶
In [18]:
2+3
Out[18]:
In [19]:
2-3
Out[19]:
In [20]:
6/3
Out[20]:
In [21]:
6*3
Out[21]:
In [22]:
12%5
Out[22]:
In [25]:
154//5
Out[25]:
In [26]:
2**4
Out[26]:
In [27]:
"hello"+" world"
Out[27]:
In [28]:
_ #last non-assigned value
Out[28]:
Bools and Comparisons¶
In [1]:
a = True
b = False
c = False
In [3]:
%whos
In [7]:
print(a and b)
print(b and c)
print(a or b)
print(b or c)
not(c)
Out[7]:
In [10]:
c = (2>3)
print(type(c))
print(c)
Useful Functions¶
In [14]:
print(round(4.7889)) #round() function
print(round(4.7889,3)) #argument for number of numbers after decimal
In [17]:
print(divmod(25,2)) #divmod() function . returns back qoutient and remainder
print(divmod(25,7))
In [23]:
print(isinstance(1,int)) #isinstance() function. checks for condition
print(isinstance(1.0,int))
print(isinstance(1.0,(int,float)))
In [24]:
print(pow(2,3)) #pow() function
print(pow(2,3,3)) #finds power of first two args and finds mod with 3rd argument
In [ ]:
v = input("Enter a number")#input()
v = float(v) #changing datatype
Control Flow¶
In [8]:
print("The largest number will be printed.")
a = int(input("Enter a: "))
b = int(input("Enter b: "))
if a>b:
print(a)
elif a<b:
print(b)
else:
print("You entered the same numbers")
In [10]:
#if else ,if elif else, nested if,while,for..same as i know
Function def¶
In [1]:
def prints():
"""prints hi"""
print("Hiiii")
In [25]:
prints();
In [28]:
#fun(x,y); supplying variables
In [3]:
#return ___
In [4]:
def add(*args): #variable number of arguments
sum = 0
for i in range(len(args)):
sum+=args[i]
return sum
In [7]:
print(add(1,2,3))
In [8]:
print(add(234,234,56,35,676))
MODULES¶
In [25]:
import sys
sys.path.append('/root/Desktop/')
import mymod as mod
from mymod import numeric as num
In [26]:
num(True)
Out[26]:
STRING¶
In [59]:
s = 'abc'
t = "123"
print(type(s))
print(s+" and "+t)
In [64]:
ms = ''' hi
heyy
heyyyyyyyaaa'''
print(ms)
In [84]:
a = " Game of Thrones"
print(len(a))
print(a[8:17])
print(a[-7:17])
print(a[-7:])
print(a[0:17:5])
print(a[::-1])
print(a.lower())
print(a.upper())
print(a.strip())
print(a.replace("o","23"))
In [85]:
"abc" in "awgtfrhyjgfds"
Out[85]:
In [86]:
"abc" in "abckedfrgtygfdsbac"
Out[86]:
In [87]:
"sadfgFDsas" not in "edrftyhugjg"
Out[87]:
In [92]:
print("I am \"THE\" hero")
In [93]:
print('I am "THE" hero')
In [98]:
print("C:\name\drive")
print(r"\C:\name\drive")
DATA STRUCTURES¶
List :ordered changeable duplicates¶
Tuple :ordered unchangeable duplicates¶
Set :unordered addable/removable no duplicates¶
Dictionary :unordered changeable no duplicates¶
In [106]:
L = [1,3,4,9,"name",8]
T = (1,3,4,9,"name",8)
S = {1,3,4,4,9,"name",8}
D = {23:"twenty-three","t":23,"bcd":"are"}
In [107]:
print(type(L))
print(type(T))
print(type(S))
print(type(D))
In [108]:
print(L[3])
print(T[3])
print(3 in S)
print(D[23])
print(D["bcd"])
In [110]:
L[1:3]
Out[110]:
In [111]:
T[1:3]
Out[111]:
In [115]:
L = L+[12,"AD"]
print(L)
In [116]:
L.append(899)
print(L)
In [117]:
T2 = (1,3)
In [118]:
T3 = T2 + T
In [119]:
print(T3)
In [122]:
S.update({"hiii",234})
print(S)
In [123]:
D["neww"] = "NEWWW"
In [124]:
print(D)
In [125]:
D2 = {"hi":123}
In [130]:
L2 =L.copy() #same with set,dictionary
L2
Out[130]:
In [132]:
L3 = L[1:5] #slicing picks a copy by default
L3
Out[132]:
In [135]:
help(L.append)
In [136]:
L4 = [x**4 for x in range(5)]
In [137]:
L4
Out[137]:
NUMPY¶
In [4]:
import numpy as np
a = np.array([1,2,3,4,5])
b = np.array((1,2,3,4,5))
print(a)
print(b)
print(type(a))
print(type(b))
In [8]:
c = np.array([234,34,2345],dtype="int")
type(c)
Out[8]:
In [9]:
c.dtype
Out[9]:
In [10]:
import numpy as np
a = np.array([[1,2,3],[4,5,6]])
In [11]:
a.ndim
Out[11]:
In [12]:
a[0,2]
Out[12]:
In [13]:
a[1,2]
Out[13]:
In [19]:
b = np.array([[1,2,3,4],[5,6,7,8]])
In [20]:
b.ndim
Out[20]:
In [21]:
b[0,3]
Out[21]:
In [27]:
c = np.array([[[1,2,3],[4,5,6],[3,4,5]],[[1,-2,3],[4,5,6],[3,4,5]]])
In [24]:
c.ndim
Out[24]:
In [28]:
c[1,0,1]
Out[28]:
In [29]:
c.shape
Out[29]:
In [32]:
print(c.size)
print(c.nbytes)
In [33]:
d = np.arange(100)
In [34]:
d
Out[34]:
In [39]:
d = np.arange(0,101)
In [40]:
d
Out[40]:
In [41]:
d = np.arange(0,11,2)
In [42]:
d
Out[42]:
In [43]:
np.random.permutation(np.arange(10))
Out[43]:
In [45]:
np.random.randint(20,300)
Out[45]:
In [52]:
f = np.random.rand(100)
In [53]:
print(f)
In [54]:
import matplotlib.pyplot as plot
In [56]:
plot.hist(f)
Out[56]:
In [57]:
c = np.random.rand(2,3)
c
Out[57]:
In [58]:
c.ndim
Out[58]:
In [59]:
c = np.random.rand(2,3,4,4)
c
Out[59]:
In [60]:
c.ndim
Out[60]:
In [61]:
d = np.arange(100).reshape(4,25)
d
Out[61]:
In [62]:
a = np.arange(100)
b = a[3:10]
print(b)
In [63]:
b[0] = -10
In [64]:
a
Out[64]:
In [65]:
a[::-5]
Out[65]:
In [66]:
a
Out[66]:
In [67]:
a+12
Out[67]:
In [68]:
a.sort()
In [69]:
a
Out[69]:
In [3]:
import numpy
b = numpy.random.rand(10000000)
%timeit sum(b)
In [5]:
%timeit numpy.sum(b)
In [6]:
def mysum(g):
s = 0
for x in g:
s+=x
return s
In [7]:
%timeit mysum(b)
Pandas¶
In [9]:
import pandas as pd
In [10]:
A = pd.Series([2,3,4,5],index=['a','b','c','d'])
In [11]:
A.values
Out[11]:
In [12]:
type(A.values)
Out[12]:
In [13]:
type(A)
Out[13]:
In [14]:
A.index
Out[14]:
In [15]:
A['a']
Out[15]:
In [16]:
A['a':'c']
Out[16]:
In [20]:
grades_dict = {"A":4,"B":3,"C":2,"D":1}
grads = pd.Series(grades_dict)
In [21]:
grads.values
Out[21]:
In [23]:
marks_dict={"A":80,"B":60,"C":40,"D":20}
marks = pd.Series(marks_dict)
In [24]:
marks
Out[24]:
In [25]:
marks.values
Out[25]:
In [26]:
marks["A"]
Out[26]:
In [27]:
res = pd.DataFrame({'Marks':marks,'Grades':grads})
In [28]:
res
Out[28]:
In [29]:
res.T
Out[29]:
In [31]:
res.values
Out[31]:
In [32]:
res.values[0,1]
Out[32]:
In [35]:
res['Percentage(out of 90)']=100*(res['Marks']/90)
In [36]:
res
Out[36]:
In [37]:
del res['Percentage']
In [38]:
res
Out[38]:
In [41]:
g = res[res['Marks']>60]
In [42]:
g
Out[42]:
In [43]:
z = pd.DataFrame([{'a':1,'b':2},{'b':3,'c':4}])
In [44]:
z
Out[44]:
In [45]:
z.T
Out[45]:
In [47]:
z.fillna(0)
Out[47]:
In [50]:
z.dropna() #drops all rows which has na
Out[50]:
In [52]:
z
Out[52]:
In [55]:
a = pd.Series(['a','b','c'],index=[1,3,5])
In [56]:
a[1]
Out[56]:
In [57]:
a[1:3]
Out[57]:
In [58]:
a.loc[1:3]
Out[58]:
In [59]:
a.iloc[1:3]
Out[59]:
In [62]:
#pd.read_csv('path')
#df.head(n)
#df.drop(['Sno',..],axis=1,inaplce=True)
#df.rename(columns={'ObservationDAte':'Date'},inaplce=True)
#df.info
#df.fillna(NA)
#df.groupby('')
In [64]:
import matplotlib.pyplot as plt
import numpy as np
In [66]:
x = np.linspace(0,10,1000)
print(x)
plt.plot(x,np.sin(x));
In [69]:
plt.scatter(x[::10],np.sin(x)[::10],color='red')
Out[69]:
In [ ]: