#!/usr/bin/env python
# coding: utf-8

# ## CAOS Workshop Series: Introduction to Python Programming

# ### Chris McCray - 21 February 2018

# Basic Python syntax (from https://www.stavros.io/tutorials/python/)

# * Python has no mandatory statement termination characters (i.e. semicolons)
# * Single-line comments start with a #
# * Variable values are assigned using =
# * Python automatically sets the data type (i.e. int, float, str)
# * Basic data structures: lists, tuples, dictionaries (index of the first item is 0)

# Python allows for a great deal of freedom, but does have a style guide (PEP 8) to make your code generally cleaner and more user-friendly: https://www.python.org/dev/peps/pep-0008/
# 
# Many good intro to Python resources can be found online (check them out for more detail than we can go through here) - e.g., Python tutorial: https://docs.python.org/3/tutorial/
# 
# Python code can be run in scripts, with an IDE (see Spyder), in Jupyter notebooks like this one

# Jupyter Notebook:
# * Allows code to be run in blocks/"cells"
# * Allows for easy presentation of figures and code
# * Can be hosted remotely (i.e. on a server, closer to your data)

# ### Variables, data types, and printing

# Variable types are automatically assigned - no type declarations needed
# 
# Variable names 
# * Can start with lowercase or uppercase letters (but not numbers or symbols!)
# * Can contain numbers and certain symbols
# * Words should be separated by underscores
# 
# Printing
# * In Python 3, printing output requires parentheses: print(variable_name)
# * In Python 2, parentheses are not required (but can be included): print variable_name

# In[1]:


#Integers
my_integer = 3
print(type(my_integer))

#Floats
my_float = 1.23
print(type(my_float))

#Strings
string_1 = 'This is a string.'
string_2 = "This is also a string!"
print(type(string_1))


# In[2]:


print(my_integer)
print('Test')
print('Test',my_integer)


# In[3]:


print(string_1+my_integer)


# In[ ]:


print(string_1+' '+str(my_integer))


# In[4]:


print(string_1, my_integer)


# ### Lists and dictionaries

# ##### Lists

# In[5]:


list_one = ['a','b','c','d','e','f']
print(list_one[0])
print(list_one[-1])


# ![image.png](attachment:image.png)

# ##### Dictionaries

# In[6]:


ages = {'Jim': 23, 
        'Sarah': 25,
        'Tom': 30}


print(ages['Jim'])


# ### Control Flow Tools/Loops

# ##### While loop

# In[7]:


b = 10
while b <= 20:
    print (b)
    b+=1


# ##### If statements

# In[9]:


x = int(input("Please enter an integer:"))
if x < 0:
    print(x,'is less than 0.')
elif x == 0:
    print(x,'is 0.')
else:
    print(x,'is greater than 0.')


# ##### For loop

# In[10]:


words = ['cat', 'horse', 'chicken']
for w in words:
    print(w, len(w))


# ### Modules and functions

# * Python source files (ending in .py) are known as **modules**
# * Modules contain **functions**, which can be called separated from the module
# * Below is an example of what's inside the module _welcome.py_ (modified from https://developers.google.com/edu/python/introduction)
# * Try running welcome.py by typing ```python hello.py``` and your name, in your command line

# ```python
# #!/usr/bin/env python
# 
# # import modules used here -- sys is a very standard one
# import sys
# 
# # Gather our code in a main() function
# def main():
#     print('Hello there', sys.argv[1])
#     # Command line args are in sys.argv[1], sys.argv[2] ...
#     # sys.argv[0] is the script name itself and can be ignored
# 
# def string_information(string):
#     num_characters = len(string)
#     num_no_whitespace = (len(string.replace(" ", "")))
#     print('This string has',num_characters,'characters including \\
#     whitespace and',num_no_whitespace,'without whitespace.')
# 
# # Standard boilerplate to call the main() function to begin
# # the program.
# if __name__ == '__main__':
#     main()
# 
# ```

# Functions can be imported into other modules:
# (welcome.py can be downloaded at https://github.com/mccrayc/tutorials/blob/master/1_intro/welcome.py)

# In[ ]:


from welcome import string_information


# In[ ]:


string = 'This Is a Test'
string_information(string)


# ### Basic Math

# In[13]:


print( 3.1 + 3.6 )
print( 3.1/392   )
print( 3.1*3.2   )
print( 4**2  )


# In[14]:


import math
from math import cos
print( cos(2*math.pi) )
print( math.sqrt(4) )


# #### Warning: In Python 2, integer division is "floor division"
# * 5/6 = 0
# * 6/5 = 1

# #### NumPy
# From http://www.numpy.org/
# > NumPy is the fundamental package for scientific computing with Python. It contains among other things
# * a powerful N-dimensional array object
# * sophisticated (broadcasting) functions
# * tools for integrating C/C++ and Fortran code
# * useful linear algebra, Fourier transform, and random number capabilities
# "

# In[15]:


import numpy as np


# In[16]:


a = np.array([[1,2,3,4],[5,6,7,8]])
print(a)


# In[17]:


#Subtract 3 from each array element
print( a-3 )
# Get the cosine of each array element
print( np.cos(a) )
# Calculate e^x for each array element x
print (np.exp(a))
# Transpose a
print( a.T )


# NumPy is a very important part of scientific Python, and forms an integral part of nearly all other scientific packages. You should look through https://docs.scipy.org/doc/numpy-dev/user/quickstart.html to get some background in how it works.

# ### Plotting with matplotlib

# The most common plotting library with Python is currently [matplotlib](https://matplotlib.org/), which provides a MATLAB-style interface
# 
# * There are many ways to create figures and subplots with matplotlib, but here we'll just go over a basic example using the pyplot interface.
# * Pyplot provides MATLAB-like functionality

# In[18]:


import matplotlib.pyplot as plt


# In[19]:


'''
This allows for an interactive figure interface within the jupyter notebook. 
If you just want to show the figure without interactivity, use %matplotlib inline
'''
get_ipython().run_line_magic('matplotlib', 'notebook')


# In[20]:


x = np.arange(0,100,0.01)
y1 = np.cos(x)
y2 = np.sin(x)


# In[21]:


plt.plot(x,y1, label='cos(x)')
plt.plot(x,y2, label='sin(x)')
plt.axhline(y=0, color='k')


# In[22]:


#Zoom in on the plot
plt.xlim([0,10])


# In[ ]:


#Add labels to the axes
plt.xlabel("x")
plt.ylabel("y")
#Add a title
plt.title("$sin(x)$ and $cos(x)$")
#Add a grid
plt.grid()


# In[23]:


#Plot a basic legend
plt.legend()


# In[24]:


plt.close()


# ### Exercise: Working with real data (CSV format) in Pandas

# * There are many ways to read CSV data. Python's standard library includes the "csv" package
# * "Pandas" (https://pandas.pydata.org/) is one of the key packages in scientific Python and data science
# * Pandas makes reading CSVs easy, handles missing data well, and allows for quick calculations and plotting
# 

# In[25]:


import pandas as pd


# We'll read in a CSV file that contains daily weather data for each day in 2017 from Environment and Climate Change Canada for CYUL (Montreal-Trudeau Airport)

# In[26]:


cyul_2017 = pd.read_csv('http://www.cdmccray.com/python_tutorial/eng-daily-01012017-12312017.csv')


# In[27]:


cyul_2017


# In[28]:


#Set the index of the Pandas DataFrame to Date
cyul_2017.set_index('Date', inplace=True)


# In[29]:


cyul_2017


# In[30]:


cyul_2017.loc['2017-05-29']


# Let's see what the warmest and coldest temperatures of 2017 were:

# In[31]:


cyul_2017['Tmax'].nlargest(5)


# In[32]:


cyul_2017['Tmin'].nsmallest(5)


# #### Now, let's try plotting some of this data

# First, we'll grab the individual columns we want for our x and y data

# In[33]:


max_temps = cyul_2017['Tmax']


# In[34]:


max_temps


# In[35]:


plt.figure(figsize=[7,4])
plt.plot(max_temps)


# Pandas has many convenience functions that allow us to quickly plot our data in a much prettier way!

# In[36]:


plt.close()
plt.figure()
cyul_2017['Tmax'].plot(color='red', figsize=[8,5])
cyul_2017['Tmin'].plot(color='blue')


# #### Let's add a 30-day rolling average to the plot so that we smooth out the variations
# 

# In[38]:


cyul_2017['Tmean'].rolling(30,min_periods=2,center=True).mean().plot(c='k', label='30-day avg. Tmean')

plt.grid()


# #### Now, add a title, axis labels, and legend

# In[39]:


plt.title('Montreal Daily Temperatures - 2017')
plt.ylabel('Temperature (deg C)')
plt.legend()


# #### With pandas, you can do quick statistics/calculations as well. This is what makes it really powerful for data analysis

# In[40]:


cyul_2017.describe()


# In[41]:


cyul_2017[cyul_2017.Month==12].describe()


# ### Try making a plot of one of the other fields in cyul_2017

# In[ ]:


plt.close()
#######


# ## Other useful AOS-related Python packages

# * Xarray - reading, analyzing, editing, creating NetCDF files

# * MetPy - https://unidata.github.io/MetPy/latest/
#     * Meteorological functions and calculations ($\theta_e$, RH, dew point, etc.)
#     * Plotting Skew-T diagrams, station plots, radar data, etc.

# * Cartopy - http://scitools.org.uk/cartopy/
#     * Plotting data on maps
#     * Note that you'll come across matplotlib basemap - this is no longer developed and Cartopy is currently the successor to basemap