在Python表格中使用for循环

Question

我正在尝试制作一个表格，用来整理高票房电影和与它们最相似的电影。我的代码已经写好了，但在完成表格时遇到了一些麻烦。

我的代码：

#import the data from the csv file and use DictRead to interpret the information.

import csv

csv_file = open("moviestats_med.csv")
csv_data = csv.DictReader(csv_file)


#create dictionary of films and their directors.
direct = {}
#create dictionary of films and their genres.
genre = {}
#create dictionary of films and each main actor.
actor1 = {}
actor2 = {}
actor3 = {}
#create dictionary of films and their worldwide gross.
gross = {}
#create dictionary of films and the year they came out.
year = {}

name = {}
#iterate over the csv file to fill the dictionaries.
for c in csv_data:
    direct[c['name']] = c['director']
    genre[c['name']] = c['genre']
    actor1[c['name']] = c['actor1']
    actor2[c['name']] = c['actor2']
    actor3[c['name']] = c['actor3']
    gross[c['name']] = c['Worldwide Gross']
    year[c['name']] = c['date']
    name[c['name']] = c['name']    

#create a two-variable function to deterime the FavActor Similarity score:
def FavActorFunction(film1,film2):
    #set the result of the FavActor formula between two films to a default of 0.
    FavActorScore = 0
    #add 3 to the similarity score if the films have the same director.
    if direct[film1] == direct[film2]:
        FavActorScore += 3
    #add 2 to the similarity score if the films are in the same genre.
    if genre[film1] == genre[film2]:
        FavActorScore += 2
    #add 5 to the similarity score for each actor they have in common.                    
    if actor1[film1] in (actor1[film2], actor2[film2], actor3[film2]):
        FavActorScore += 5
    if actor2[film1] in (actor1[film2], actor2[film2], actor3[film2]):
        FavActorScore += 5
    if actor3[film1] in (actor1[film2], actor2[film2], actor3[film2]):
        FavActorScore += 5    
    #print the resulting score.                    
    return FavActorScore

#create a function to find the film with the greatest Worldwide Gross per year.   
def MaxGrossFinder(c):
    #set the intial maximum gross to zero.
    MaxGross = 0  
    #replace the MaxGross with any film in that year that has a greater gross.
    for film in year:                      
        f = int(gross[film])                        
        if year[film] == c:
            if f > MaxGross:
                MaxGross = f
                max = film
    #print the year and the max value for that year.                   
    return max

#create a dictionary for the max grossing films of each year from 2000-2007.
max_films = {}                       
#create a list of years from 2000-2007.                       
for c in ['2000', '2001', '2002', '2003', '2004', '2005', '2006', '2007']:
    max_films[c] = MaxGrossFinder(c)



if 'a' == 'a':
    max_list = []
    MaxSimilarity = 0
    for d in year:
        f = FavActorFunction(max_films[c], d)    
        if d != MaxGrossFinder(c):
            if year[d] == c:
                if f > MaxSimilarity:
                    MaxSimilarity = f
                    max = d
    max_list.append(max)

    MaxSimilarity2 = 0            
    for d in year:
        g = FavActorFunction(max_films[c], d)    
        if d != MaxGrossFinder(c):
            if d != max:
                if year[d] == c:
                    if g > MaxSimilarity2:
                        MaxSimilarity2 = g
                        max2 = d
    max_list.append(max2)

    MaxSimilarity3 = 0            
    for d in year:
        h = FavActorFunction(max_films[c], d)    
        if d != MaxGrossFinder(c):
            if d != max and d != max2:
                if year[d] == c:
                    if h > MaxSimilarity3:
                        MaxSimilarity3 = h
                        max3 = d

    max_list.append(max3)



    MaxSimilarity4 = 0            
    for d in year:
        i = FavActorFunction(max_films[c], d)    
        if d != MaxGrossFinder(c):
            if d != max and d != max2 and d != max3:
                if year[d] == c:
                    if i > MaxSimilarity4:
                        MaxSimilarity4 = i
                        max4 = d
    max_list.append(max4)




print "Content-Type: text/html"
print ""
print "<html>"
print "<body>"
print "<table border=1>"

print "<tr>"
print "<th><font color=green>Year</font></th>"
print "<th><font color=blue>Highest Grossing Film</font></th>"
print "<th><font color=red>Most Similar</font></th>"
print "<th><font color=red>2nd Most Similar</font></th>"
print "<th><font color=red>3rd Most Similar</font></th>"
print "<th><font color=red>4th Most Similar</font></th>"
print "</tr>"


for c in sorted(max_films):
    print "<tr><th>"
    print c
    print "<td>"
    print max_films[c]
    print "</td><td>"
    print max_list[0]
    print "</td><td>"
    print max_list[1]
    print "</td><td>"
    print max_list[2]
    print "</td><td>"
    print max_list[3]
    print "</td></tr></th>"

我做出来的表格大部分是正确的，但每一行的“最相似”电影都对应到第一个年份[2000]。我该如何修改我的代码，让“最相似”的电影能对应到正确的数据呢？

循环控制表格处理数据整理相似度计算高票房电影

在Python表格中使用for循环

2 个回答

撰写回答