import pandas as pd

# Let's start with simple example of appending to a list
listA = [1,2,3,4]
listB = [1,2,3,4]

listA.append(5) # we modify lists, using listName.append(value)

print(listA)
print(listB)

# now we have added a value to our list

# we can copy a list by setting it equal to a new variable
# ...neat
# but what will happen if you add to one of these lists?

list1 = [1,2,3,4]
list2 = list1
list2.append(5) # Modifying list2 also modifies list1 because they reference the same list

print(list1)
print(list2)

# DataFrame in pandas

    # A DataFrame can be created from a dictionary of lists
    # Each key-value pair in the dictionary corresponds to a column in the DataFrame
    # The key is the column label and the list is the column data
data = {
    'mag': [1,1,3,3], # column 1
    'date': ['April 10 2024','April 11 2024','April 12 2024','April 13 2024'], # column 2
    'inj' : [1,2,100,200] # column 3
}
tdata = pd.DataFrame(data) #convert to a pandas Dataframe
print(tdata)  # lets have a look before changing anything

# A DataFrame is like a dictionary of lists, but with additional functionality

# Be careful when modifying DataFrames OR lists
# If you create a new DataFrame OR list by referencing an existing one, they will both point to the same data
cleaned_tdata = tdata

# So if you modify one, the other will also be modified
cleaned_tdata.drop('mag', axis=1, inplace=True)

print(tdata)
print(cleaned_tdata)

# we dropped mag in the cleaned tdata
# But that change was also applied to the tdata!

# Lets try dropping a single row, again notice how this change carries over to the data we 'copied'?



data = {
    'mag': [1,1,3,3], # column 1
    'date': ['April 10 2024','April 11 2024','April 12 2024','April 13 2024'], # column 2
    'inj' : [1,2,100,200] # column 3
}
tdata = pd.DataFrame(data)

# We create a 'copy' of the data that we want to work on or clean
cleaned_tdata = tdata

# Drop the specified rows from the DataFrame in-place
# modify one, the other will also be modified
cleaned_tdata.drop(cleaned_tdata[cleaned_tdata['mag'] == 1].index, inplace=True)

print(tdata)
print(cleaned_tdata)

# To avoid this, create a real copy of the data
data = {
    'mag': [1,1,3,3], # column 1
    'date': ['April 10 2024','April 11 2024','April 12 2024','April 13 2024'], # column 2
    'inj' : [1,2,100,200] # column 3
}
tdata = pd.DataFrame(data)

# create a REAL copy of the data to work on or clean
cleaned_tdata = tdata.copy()  # creates a real copy of the data

# Drop the specified rows from the DataFrame in-place
cleaned_tdata.drop(cleaned_tdata[cleaned_tdata['mag'] == 1].index, inplace=True)

print(tdata) # The original data is unchanged
print(cleaned_tdata)

# Did we really mean to also modify the original tdata?...
# Why did this happen?
    # we dropped rows from cleaned_tdata 'in-place', which modified the original data for cleaned_tdata
    # since tdata and cleand_tdata both point to the same DataFrame
    # modifying the orignal data frame (i.e., using inplace=True) also affects tdata

# To avoid changing/losing the original data, best to create a REAL copy using .copy()  BEFORE making any changes to the data

# use the tuple as a multi-index in the DataFrame. 
# This allows you to index the DataFrame using the values in multiple columns

# Create a DataFrame from a dictionary of tuples
data = {
    'mag': (1,1,3,3),
    'date': ('April 10 2024','April 11 2024','April 12 2024','April 13 2024'),
    'inj' : (1,2,100,200)
}
tdata = pd.DataFrame(data)

# Set 'mag' and 'date' as a multi-index
tdata.set_index(['mag', 'date'], inplace=True)
new_tdata= tdata
print(tdata)
print(new_tdata)

# Access data for a specific 'mag' and 'date'
print(tdata.loc[(1, 'April 11 2024')])


# Access data for a specific 'mag' and 'date'
print(new_tdata.loc[(1, 'April 11 2024')])

# Try to change the 'mag' value for a specific row in the index
try:
    tdata.index[0] = (2, 'April 11 2024')
except TypeError as e:
    print(f"TypeError: {e}")

# Try to change the 'date' value for a specific row in the index
try:
    tdata.index[0] = (1, 'April 12 2024')
except TypeError as e:
    print(f"TypeError: {e}")

# To change the mag or date values for a specific row
# need to create a new tuple, which means creating a new dataframe

# .resetindex() Creates NEW DataFrame, applied on tdata will remove the multi-index 
# reverts tdata back to default integer index, with mag and date as columns
tdata_copy = tdata.reset_index()  # tdata_copy is a separate object and does not reference the same data

print(tdata) # original data is maintained
print(tdata_copy) # a new separate dataframe is created


# Now that mag and date are not a tuple, we can change the 'mag' and 'date' values
tdata_copy.loc[0, 'mag'] = 5   # changes mag in the first row
tdata_copy.loc[0, 'date'] = 'June 1 2024' # changes date in the first row

# Set the new multi-index
tdata_copy.set_index(['mag', 'date'], inplace=True)


print(tdata)
print(tdata_copy) # even though it is derived from tdata, it a separate object and changes to one will not affect the other

# In this example, we're setting 'mag' and 'date' as a multi-index for the DataFrame
# This allows us to index the DataFrame using the values in both 'mag' and 'date'. The tuple of ('mag', 'date') 
#     acts as a single key that we can use to index the DataFrame
# This is a case where the immutability of tuples is relevant to the analysis of data in a DataFrame.
    # Similar to how in functional programming,
    # the immutability of data structures ensures that their identity remains constant even as new data structures are created based on them

# Say we find that we often need to change the data in our dataframe, maybe dates and mags have typos..
# We need a function to simplify this re-occuring process 
# but our dataframe has a tuple multi index
# So, our function should take a dataframe, and a tuple, then return a NEW dataframe with the updated index

def set_new_index(df, row, new_index_values):

    print(df) #input data we want to change

    # Create a new DataFrame with the desired index
    df_copy = df.reset_index() # reset the index and create a NEW dataframe

    print(df_copy) # check the results of the NEW dataframe

    df_copy.loc[row, ['mag', 'date']] = new_index_values # change the mag and date for the first row of the NEW dataframe

    print(df_copy)

    df_copy.set_index(['mag', 'date'], inplace=True) # set the index to the tuple of mag, date for the NEW dataframe

    print(df_copy)

    return df_copy # return the NEW dataframe with the modified index

# This pure function , it doesn't modify the original DataFrame (it has no side effects)
# will always product the same output Dataframe for the same input Dataframe,index (we have no external variables in the function modifying our output)

new_tdata = set_new_index(tdata, 0, (2, 'April 12 2024')) # creates a new DataFrame with the multi index (tuple) updated

print(new_tdata)

# This function doesn't modify the original DataFrame (no side effects)