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

# <img src="../../img/header_imdb.png" alt="Drawing" style="width: 1000px;"/>  
# 
# 
# ### Which genre contains the longest movies on average, and how long are they?
# 

# ### Find the highest ranked movie per genre

# ### Find the longest movie per year

# ### Can you print the previous output sorted by year?
# 
# <br></br>
# <br></br>

# ### Answers

# <b>Which genre contains the longest movies on average, and how long are they?</b>

# In[1]:


fh        = open('../../downloads/250.imdb', 'r', encoding = 'utf-8')
genreDict = {}

for line in fh:
    if not line.startswith('#'):
        cols    = line.strip().split('|')
        genre   = cols[5].strip()
        glist   = genre.split(',')
        runtime = cols[3]
        for entry in glist:
            if not entry.lower() in genreDict:
                genreDict[entry.lower()] = [int(runtime)]
            else:
                genreDict[entry.lower()].append(int(runtime))
fh.close()
                
longest = [0,'']        # save the longest genres
for genre in genreDict:
    average = sum(genreDict[genre])/len(genreDict[genre])
    if average > longest[0]:
        longest = [average, genre]

hours   = longest[0]/3600
minutes = (longest[0] - (3600*int(hours)))/60
print(longest[1]+' is the genre with the longest movies at '+str(int(hours))+'h'+str(round(minutes))+'min')


# <b>Find the highest ranked movie per genre</b>

# In[3]:


fh        = open('../../downloads/250.imdb', 'r', encoding = 'utf-8')
genreDict = {}  

for line in fh:
    if not line.startswith('#'):
        cols   = line.strip().split('|')
        rating = float(cols[1].strip())
        movie  = cols[6].strip()
        genre  = cols[5].strip()
        glist  = genre.split(',')
        for entry in glist:
            if not entry.lower() in genreDict:              # if genre in dictionary, add first movie
                genreDict[entry.lower()] = [rating, movie] 
            else:
                if rating > genreDict[entry.lower()][0]:    # only replace if rating is higher
                    genreDict[entry.lower()] = [rating, movie]  
fh.close()

for genre in genreDict:
    print('The best movie for '+genre.capitalize()+' is:\n\t'+genreDict[genre][1]+' ('+str(genreDict[genre][0])+')')


# <b>Find the longest movie per year</b>

# In[5]:


fh        = open('../../downloads/250.imdb', 'r', encoding = 'utf-8')
yearDict = {}  

for line in fh:
    if not line.startswith('#'):
        cols   = line.strip().split('|')
        year   = int(cols[2].strip())
        length = int(cols[3].strip())
        movie  = cols[6].strip()
        if not year in yearDict:              # if genre in dictionary, add first movie
            yearDict[year] = [length, movie] 
        else:
            if length > yearDict[year][0]:    # only replace if rating is higher
                yearDict[year] = [length, movie]  
fh.close()

for year in yearDict:
    hours   = yearDict[year][0]/3600
    minutes = (yearDict[year][0] - (3600*int(hours)))/60
    print('The longest movie for '+str(year)+' is:\n\t'+yearDict[year][1]+\
          ' ('+str(int(hours))+'h'+str(round(minutes))+'min)')


# <b>Can you print the previous output sorted by year?</b>

# In[6]:


fh        = open('../../downloads/250.imdb', 'r', encoding = 'utf-8')
yearDict = {}  

for line in fh:
    if not line.startswith('#'):
        cols   = line.strip().split('|')
        year   = int(cols[2].strip())
        length = int(cols[3].strip())
        movie  = cols[6].strip()
        if not year in yearDict:              # if genre in dictionary, add first movie
            yearDict[year] = [length, movie] 
        else:
            if length > yearDict[year][0]:    # only replace if rating is higher
                yearDict[year] = [length, movie]  
fh.close()

sorted_years = sorted(list(yearDict.keys()))

for year in sorted_years:
    hours   = yearDict[year][0]/3600
    minutes = (yearDict[year][0] - (3600*int(hours)))/60
    print('The longest movie for '+str(year)+' is:\n\t'+yearDict[year][1]+\
          ' ('+str(int(hours))+'h'+str(round(minutes))+'min)')