STAT1013: Data Science Overview

from IPython.display import YouTubeVideo
YouTubeVideo('inN8seMm7UI')

!pip install numpy pandas seaborn scikit-learn

import numpy as np
print(np.__version__)

import pandas as pd
print(pd.__version__)

## int
1 + 1

x = 4
type(x)

## float
x = 2.1
type(x)

## Booleans
1 > 2

x = (1 > 2)
type(x)

## Type conversion (casting):
float(1)

## arithmetic operation
x, y = 3, 2
print(x + y) 
print(x - y) 
print(x * y) 
print(x / y) 
print(x // y) 
print(x % y) 
print(-x) 
print(abs(-x)) 
print(int(3.9)) 
print(float(x)) 
print(x ** y) 

## lists
colors = ['red', 'blue', 'green', 'black', 'white']
print(colors)

type(colors)

## Indexing: accessing individual objects contained in the list:
colors[0]

colors[-1]

colors[2:4]

## Dictionaries
tel = {'emmanuelle': 5752, 'sebastian': 5578}

tel

tel['francis'] = 5915
tel

tel['sebastian']

## function
def add(x, y):
    return x+y

z = add(x=1,y=1)
print(z)

## position argument
z = add(1,2)
print(z)

## default argument
def add(x, y=10):
    return x+y

add(1)

## if/elif/else
if 2**2 == 4:
    print('correct!')

## step function
## f(x) = 1 if x <0; f(x)=0, if 0<=x<=1, f(x)=-1, if x>1
def step_fun(x):
    if x < 0:
        return 1
    elif x> 1:
        return -1
    else:
        return 0

step_fun(100)

step_fun(.5)

step_fun(-5)

## For loop
for i in range(5):
    print(i)

## loop over a list
for name in ['A', 'B', 'C', 1, 5, 'eric']:
    print(name)

import pandas as pd

## load from website
df = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/fmri.csv')
df.head(5)

## header option in read_csv
df = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/fmri.csv', header=0)
df.head(5)

## load from csv file
df = pd.read_csv('fmri.csv')

## read partial columns
df.columns

## single column
df['timepoint']

## multiple columns
df[['subject', 'timepoint']]

## select one row
df.iloc[0]

## select many rows
df.iloc[0:10]

## select many rows
df.iloc[[1,5,7]]

## conditional select
df[df['region'] == 'parietal']

df[df['signal'] > 0]

df[(df['signal'] > 0) & (df['region'] == 'parietal')]

## generate columns from existing columns
df['period'] = df['timepoint'] > 5

df

## more about panads
from IPython.display import YouTubeVideo
YouTubeVideo('vmEHCJofslg')

## array
import numpy as np

a = np.array([1, 2, 3])   # Create a rank 1 array
print(type(a))            # Prints "<class 'numpy.ndarray'>"
print(a.shape)            # Prints "(3,)"
print(a[0], a[1], a[2])   # Prints "1 2 3"
a[0] = 5                  # Change an element of the array
print(a)                  # Prints "[5, 2, 3]"

b = np.array([[1,2,3],[4,5,6]])    # Create a rank 2 array
print(b.shape)                     # Prints "(2, 3)"
print(b[0, 0], b[0, 1], b[1, 0])   # Prints "1 2 4"

a = np.zeros((2,2))   # Create an array of all zeros
print(a)              # Prints "[[ 0.  0.]
                      #          [ 0.  0.]]"

b = np.ones((1,2))    # Create an array of all ones
print(b)              # Prints "[[ 1.  1.]]"

c = np.full((2,2), 7)  # Create a constant array
print(c)               # Prints "[[ 7.  7.]
                       #          [ 7.  7.]]"

d = np.eye(2)         # Create a 2x2 identity matrix
print(d)              # Prints "[[ 1.  0.]
                      #          [ 0.  1.]]"

## array index
import numpy as np

# Create the following rank 2 array with shape (3, 4)
# [[ 1  2  3  4]
#  [ 5  6  7  8]
#  [ 9 10 11 12]]
a = np.array([[1,2,3,4], [5,6,7,8], [9,10,11,12]])

a[1:3, 2:3]

## conditional select
a[a>8]

## casting
x = np.array([1, 2], dtype=np.int64)

print(x)

np.array(x, dtype=np.float32)

## Math operators

## note: do not conduct math based on a list

## add scalar
a = np.array([1, 2, 3, 4])
a + 1

## two array
b = np.ones(4) + 1
a - b

## mat elementwise operator
c = np.ones((3, 3))
c+c

c*c

## matrix operator
np.dot(c, c) # or c.dot(c)

## some basic functions
x = np.array([1, 2, 3, 4])
x.sum()

np.sort(x)

x.min()

x.argmin()

## matrix operator
x = np.array([[1, 1], [2, 2]])
x.sum()

x.sum(axis=0)

x.sum(axis=1)

x.min()

x.min(axis=0)

from IPython.display import YouTubeVideo
YouTubeVideo('QUT1VHiLmmI')