import pandas as pd

flist = ['targaryen', 'stark', 'baratheon', 'tully', 'lannister', 'tyrell', 'martell']
alist = ['dragon','wolf','deer','fish','lion','rose','sun']
nlist = ['대너리스','에다드','로버트','브린덴','제이미','로라스','도란'];

for item in flist:
    print(item)

# make iterator from list
superspeed = iter(flist)

print(next(superspeed))
print(next(superspeed))
print(next(superspeed))

small_value = iter(range(3))

print(next(small_value))
print(next(small_value))
print(next(small_value))

googol = iter(range(10 ** 1000))   # big number - may not work

print(next(googol))
print(next(googol))

enumlist = list(enumerate(flist))   # list of tuple
print(enumlist)

for index1, value1 in enumlist:    # unpack tuple
    print(index1, value1)

for index2, value2 in enumerate(flist, start = 1):   # Change the start index
    print(index2, value2)

m_data = list(zip(nlist, flist, alist))
print(m_data)

m_zip = zip(nlist, flist, alist)   # create zip object

print(m_zip)

for value1, value2, value3 in m_zip:   # unzip
    print(value1, value2, value3)

# unzip (*)
m_zip = zip(nlist, flist, alist) 
print(*m_zip)

m_zip = zip(nlist, flist, alist) 
result1, result2, result3 = zip(*m_zip)  # unzip to tuple
print(result2)
print(flist)
print(result2 == flist)   # Check if unpacked tuples are equivalent to original tuples

counts_dict = {}

# Iterate over the file chunk by chunk
for chunk in pd.read_csv('data/tweets.csv', chunksize = 10):
    # Iterate over the column in dataframe
    for entry in chunk.lang:
        if entry in counts_dict.keys():
            counts_dict[entry] += 1
        else:
            counts_dict[entry] = 1

print(counts_dict)

# count entry function with chunksize

def count_entries(csv_file, c_size, colname):
    """Return a dictionary with counts of ccurrences as value for each key."""
    
    counts_dict = {}

    for chunk in pd.read_csv(csv_file, chunksize=c_size):
        for entry in chunk[colname]:
            if entry in counts_dict.keys():
                counts_dict[entry] += 1
            else:
                counts_dict[entry] = 1

    return counts_dict

result_counts = count_entries('data/tweets.csv', 10, 'lang')
print(result_counts)

squares = [i**2 for i in range(10)]

# Create a 5 x 5 matrix using a list of lists
matrix = [[col for col in range(5)] for row in range(5)]

for row in matrix:
    print(row)

# conditionals in comprehensions

new_fellowship = [member for member in flist if len(member) >= 7]
print(new_fellowship)

new_fellowship = [member if len(member) >= 7 else '' for member in flist]
print(new_fellowship)

# tweet_clock_time = [entry[11:19] for entry in tweet_time if entry[17:19] == '19']

# Dict comprehensions

new_fellowship = {member:len(member) for member in flist}
print(new_fellowship)

# Create a generator object
lengths = (len(person) for person in flist)

for value in lengths:
    print(value)

# [num for num in range(10**10000000)]  -- 대용량 데이터일 경우 문제 발생

# (num for num in range(10**100000))   # generator 객체 만든 후 요청시에만 처리되기 때문에 대용량 데이터 처리시 안전.

# 2개의 list 를 dictionary로 만드는 함수

def lists2dict(list1, list2):
    """list1 provides the keys and list2 provides the values."""

    zipped_lists = zip(list1, list2)
    rs_dict = dict(zipped_lists)
    return rs_dict

fa_dict = lists2dict(alist, flist)
fa_dict

feature_names = ['familyname','firstname','crest']

row_list = []
m_zip = zip(flist, nlist, alist)

for value1, value2, value3 in m_zip:
    item = (value1, value2, value3)
    row_list.append(item)
    
row_list

list_of_dicts = [lists2dict(feature_names, sublist) for sublist in row_list]
list_of_dicts

df_game = pd.DataFrame(list_of_dicts)
df_game

# Open a connection to the file
with open('data/movielens_ratings.csv') as file:

    file.readline()   # Skip the column names
    
    counts_dict = {}

    # Process only the first 1000 rows
    for j in range(1000):

        # Split the current line into a list: line
        line = file.readline().split(',')

        # Get the value for the first column:  userid
        first_col = line[0]

        # userId 별 평점 부여 횟수
        if first_col in counts_dict.keys():
            counts_dict[first_col] += 1
        else:
            counts_dict[first_col] = 1

print(counts_dict)

def read_large_file(file_object):
    """A generator function to read a large file lazily."""

    # Loop indefinitely until the end of the file
    while True:
        data = file_object.readline()

        # Break if this is the end of the file
        if not data:
            break

        # Yield the line of data
        yield data

counts_dict = {}
counts = 0

with open('data/movielens_ratings.csv') as file:
    # Iterate over the generator from read_large_file()
    for line in read_large_file(file):
        counts += 1
        if counts >= 1000:
            break
            
        row = line.split(',')
        first_col = row[0]

        if first_col in counts_dict.keys():
            counts_dict[first_col] += 1
        else:
            counts_dict[first_col] = 1
            
print(counts_dict)

file_reader = pd.read_csv('data/movielens_ratings.csv', chunksize=1000)  

# Get the first dataframe chunk
df_reader = next(file_reader)

df_reader.head()

import matplotlib.pyplot as plt
%matplotlib inline

# Initialize reader object: urb_pop_reader
urb_pop_reader = pd.read_csv('data/ind_pop_data.csv', chunksize=1000)

# Get the first dataframe chunk: df_urb_pop
df_urb_pop = next(urb_pop_reader)

# Check out specific country: df_pop_ceb
df_pop_ceb = df_urb_pop[df_urb_pop['CountryCode'] == 'AFG']
df_pop_ceb.head()

# Zip dataframe columns of interest: pops
pops = zip(df_pop_ceb['TotalPop'], df_pop_ceb['UrbanPopRatio'])

# Turn zip object into list: pops_list
pops_list = list(pops)

# Use list comprehension to create new dataframe column 'Total Urban Population'
df_pop_ceb['TotalUrbanPopulation'] = [int(tup[0] * tup[1]) for tup in pops_list]
df_pop_ceb.head()

# Plot urban population data
plt.scatter(df_pop_ceb['Year'], df_pop_ceb['TotalUrbanPopulation'])
plt.xlabel('Year')
plt.ylabel('TotalUrbanPopulation')
plt.title('Afghanistan')