## Python basics.

## Download Python from Python.org . 

## It comes with IDLE. Open IDLE.
## An alternative is to get Anaconda, from https://www.anaconda.com/download-old ,  
## but you have to enter your email and and agree to receive communications and register,
## and they send you a link to download.

## First, from terminal, install packages.

python3 -m pip install numpy
python3 -m pip install faraway
python3 -m pip install pandas
python3 -m pip install scipy
python3 -m pip install statsmodels
python3 -m pip install matplotlib.pyplot
python3 -m pip install seaborn 

## Now do python3 or open Idle.

## If your download does not work, in chapter 0 of the book at https://automatetheboringstuff.com/2e/
## it says how to figure out exactly whether you have a 64-bit or 32-bit OS.

## Once you have Python downloaded, you can go to terminal, and type python3 .

## In IDLE, I went to IDLE -> Preferences -> Keys and chose history-previous and history-next and set ## them to up arrow and down arrow.

Good free introductions to Python are https://automatetheboringstuff.com/2e and https://realpython.com/python-statistics .

Python is very inflexible when it comes to spacing and indentation.
Python code runs a bit more stably and predictably in IDLE than in terminal.
In IDLE you file -> open, then choose the file, and then select run -> run module.
Also, it is unusual how you cannot end functions and for loops with brackets but instead need returns.

2+3
7*5
12 // 2.2 # just the integer part of the division.  
12 % 2 # just the remainder.
4 ** 3 # exponents.  

the_world_is_flat = True
if the_world_is_flat:
     print("Be careful not to fall off!")

You need the indentation.

+= works as in C.
x = 2
x += 1 ## 3.

## Python is great for text manipulation.
## single or doublequotes are used for strings.
'Alice' + 'Bob'
x = "Alice" * 5
x = "rick"
x[0]
x[-1] ## last element
"i" in x

input() lets the user input a value.
len() is the length, meaning number of characters in a string.
str() converts a number into a string.

## But strings are immutable. You can't do x = "rick"; x[2] = "u".
you have to instead do
x = "rick"; newx = x[0:2] + "u" + x[3]

# This program says hello and asks for my name.
print('Hello, world!')
print('What is your name?')
myName = input()
print('It is good to meet you, ' + myName)
print('The length of your name is:')
print(len(myName))
print('What is your age?')
myAge = input()
print('You will be ' + str(int(myAge) + 1) + ' in a year.')

int(4.2) ## Just the integer part. There is also round() and float().
## int('4') converts "4" into the integer 4, but int('4.2') doesn't.
## float() works nicely in both cases.
float(4.2)
float('4.2')

Like in C, the comparison operators are ==, !=, >= etc.
and, or, and not are logical.
You don't need parentheses with if, in Python.
if statement else:
You have to have a colon and an indented block of code on the NEXT line.
elif is only executed if the preceding thing was false.

mynum = int(input())
if mynum < 5:
	print("Your number is small")
elif mynum < 7: print("Your number is medium")
elif mynum <= 8: print("Your number is large")
else: print("Your number is huge")

## You can also do while loops or for loops, as with R.

i = 1
while(i < 10):
	print("Your number is ", i,".\n")
	if i == 7:
		break
	i = i + 1
	
for i in range(10):
	print("Your number is",i,"\n")

In a for loop, continue will pass to the next value of i.

for i in range(10):
	if i == 5:
		continue
	print("Your number is",i,"\n")

for i in range(10,3,-1):
	print("your number is ",i)

import random, sys, os, math ## Modules
print(random.randint(1, 10))

# This is a guess the number game.
import random
secretNumber = random.randint(1, 20)
print('I am thinking of a number between 1 and 20.')

# Ask the player to guess 6 times.
for guessesTaken in range(1, 7):
   print('Take a guess.')
   guess = int(input())

   if guess < secretNumber:
       print('Your guess is too low.')
   elif guess > secretNumber:
       print('Your guess is too high.')
   else:
       break    # This condition is the correct guess!

if guess == secretNumber:
   print('Good job! You guessed my number in ' + str(guessesTaken) + 'guesses!')
else:
   print('Nope. The number I was thinking of was ' + str(secretNumber))

## Functions.

def mynumb():
	print("What is your number?")
	i = input()
	print("Your number is ",i)

mynumb()

## You need the return after the function for python to know it is over.
## You need () after def mynumb so it knows it is a function.

If a function like print returns nothing, what it actually returns is the value None.
Variables defined in functions are all local by default.
To change a global variable within a function, do global x

def f():
	global y
	y = 3  ## y <<- 3 

y = 2
f()
y ## it will output 3.

## lists.

x = [1,2,5]
x[0] ## 1.
x = [1,2,[10,11,12]]
x[2][2] ## 12.
x[-1] ## means the last element of x.
x[0:2] ## means x[0] and x[1]. It does not include x[2]. This is called a slice.

With lists, you can do + and *.
[1, 2, 3] + ['A', 'B', 'C'] ## [1, 2, 3, 'A', 'B', 'C']
a = [1,2,8] * 4 ## [1,2,8,1,2,8,1,2,8,1,2,8]
del a[2] ## removes the 3rd element of a.  
4 in a
8 not in a
a = [1,2,2]
size, age, hair = a

## Methods.

x = [1,2,1,5,6]
x.index(5) ## first time it appears.
x.append(5) ## makes it 1,2,1,5,6,5.
x.insert(1,7) ## makes it 1,7,2,1,5,6,5.
x.remove(1) ## removes the first instance.
x.sort()
x.reverse() ## reverses the order.
## These methods only work on lists.
## y = x.sort() doesn't work. Do x.sort(); y = x.

Tuples. They are just like lists but have ( instead of [. And tuples are immutable.

You can use tuple() or list() to convert an object to that type.

LISTS ARE STORED AS REFERENCES! So if you do y = x, and x is a list, then y is actually a reference to the same list, and if you change y you will change x.
This is not true with tuples though.

x = [1,2,3,4,5]
y = x
y[2] = 12
x
y
x = (1,2,3,4,5)
y = list(x)
z = list(x)
y[2] = 12
x
y
z ## still 1,2,3,4,5.

## More strings.

x = "It\"s mine." ## \" = " inside quotes.
\' = '. \t = tab. \n = newline. \\ = \.
r makes something a raw string. Backslashes will appear. Useful for directories.
x = r"Users\Desktop\computing"
x ## this will have double slashes now.
print(x) ## this will look correct.

Multiline strings. Use """ to start and stop. Newlines, tabs, and even quotes are saved correctly! This is great.

str(x) makes the number x into a string.

## % is useful.
name = "rick"; age = 53
x = 'My name is %s. I am %s years old.' % (name, age)
print(x)

## You can also use f before the quotes.
x = f"My name is {name}. Next year I will be {age + 1}."

x.upper() ## makes it all upper case!

## Basic statistical summaries.

x = (1,5,3)
mymean = sum(x)/len(x)

## or, use the statistics module

import statistics 
statistics.mean(x)

import statistics as st
st.mean(x)

## weighted mean
x = [1,2,5,50,5]
w = [0.1, 0.2, 0.2, 0.3, 0.2]
wmean = sum(w[i] * x[i] for i in range(len(x))) / sum(w)

## geometric mean
statistics.geometric_mean(x)

## median
statistics.median(x)

## Other summaries
statistics.mode(x)
statistics.variance(x)
statistics.stdev(x)
statistics.quantiles(x)

## Cor and regression in Python
import scipy.stats
x = (1,3,5)
y = (1,7,2)
r, p = scipy.stats.pearsonr(x, y) ## correlation and corresponding p-value
scipy.stats.linregress(x, y)

## Visual summaries

import numpy as np
import matplotlib.pyplot as plt
plt.style.use('ggplot')

x = np.random.randn(200) ## 200 N(0,1) random variables.
y = np.random.randn(200)
z = np.random.randn(200)

fig, ax = plt.subplots()
z1 = ax.boxplot((x, y, z), vert=False, showmeans=True, meanline=True,
          labels=('x', 'y', 'z'), patch_artist=True,
          medianprops={'linewidth': 2, 'color': 'purple'},
          meanprops={'linewidth': 2, 'color': 'red'})
plt.show()

fig, ax = plt.subplots()
hist, bin_edges = np.histogram(x, bins=10)
ax.hist(x, bin_edges, cumulative=False)
ax.set_xlabel('x')
ax.set_ylabel('Frequency')
plt.show()

## piechart
x, y, z = 1, 3, 5
fig, ax = plt.subplots()
ax.pie((x, y, z), labels=('x', 'y', 'z'), autopct='%1.1f%%')
plt.show()

## Some simple things require packages that don't come with Python.


## Random normals

import numpy as np
x = np.random.randn(10) ## 10 N(0,1) random variables.

x = [5,7,8,7,2,17,2,9,4,11,12,9,6]
y = [99,86,87,88,111,86,103,87,94,78,77,85,86]

plt.scatter(x, y)
plt.show() 

## For more, see Linear Models with Python by Julian Faraway.
## From the Preface, "If your sole objective is to do statistics, R is more attractive."