用python讲故事（中）

# define your corpus here as a list of text files
corpus = ["aladdin.txt",
         "lionking.txt",
         "mulan.txt",
         "hunchback.txt",
         "rescuersdownunder.txt",
         "sleepingbeauty.txt",
         "littlemermaid.txt"]
# New dict to hold data
d = {}
# Map names to input files on filesystem
root_fp = os.getcwd()
corpus_fp = os.path.join(root_fp, "texts")   # put your text files in ./texts
# print("Looking for input text files: '%s'" %corpus_fp)
for t in corpus:
    fp =os.path.join(corpus_fp, t)
    print("Reading '%s'" % t)
    with open(fp,'rb') as f:
        text_name =t.split(".")[0]  # strip .txtfile extensions
        sample_col= text_name + "_sample"
        score_col =text_name + "_sentiment"
        lines =[]  # list to receive cleaned lines oftext
        # Quicktext cleaning and transformations
        for line inf:
            ifstr(line) == str(""): # there are many blank lines in movie scripts,ignore them
               continue
            else:
               line = line.replace("\n", "").lower().strip().strip('*')  #chain any other text transformations here
               lines.append(line)
       print("  %i lines read from'%s' with size: %5.2f kb" % (len(lines), t, sys.getsizeof(lines)/1024.))
        # Constructa big string of clean text
        text =" ".join(line for line in lines)
        # split onsentences (period + space)
        delim =". "
        sentences =[_ + delim for _ in text.split(delim)]  #regexes are the more robust (but less readable) way to do this...
       merged_sentences = [delim.join(s) for s in merge(sentences, 10)]  # merge sentences into chunks
        # split onwords (whitespace)
        delim =" "
        words = [_for _ in text.split()]
       merged_words = [" ".join(w) for w in merge(words, 120)]  # merge words into chunks
        # Generate samples by sliding contextwindow
        delim =" "
        samples =[delim.join(s) for s in sample_window(merged_words, 10, 1)]
       d[sample_col] = samples
       print("   submitting %isamples for '%s'" % (len(samples), text_name))
        # API toget scores
        scores =indicoio.batch_sentiment(samples)
       d[score_col] = scores
print("\n...complete!")
 Reading'aladdin.txt'
  2639 lines readfrom 'aladdin.txt' with size: 23.18 kb
   submitting 143samples for 'aladdin'
 Reading'lionking.txt'
  3506 lines readfrom 'lionking.txt' with size: 29.42 kb
   submitting 135samples for 'lionking'
 Reading'mulan.txt'
  1231 lines read from'mulan.txt' with size:  9.97 kb
   submitting 78samples for 'mulan'
 Reading'hunchback.txt'
  2659 lines readfrom 'hunchback.txt' with size: 23.18 kb
   submitting 106samples for 'hunchback'
 Reading'rescuersdownunder.txt'
  882 lines readfrom 'rescuersdownunder.txt' with size: 7.80 kb
   submitting 82samples for 'rescuersdownunder'
 Reading'sleepingbeauty.txt'
  1084 lines readfrom 'sleepingbeauty.txt' with size: 8.82 kb
   submitting 58samples for 'sleepingbeauty'
 Reading'littlemermaid.txt'
  1103 lines readfrom 'littlemermaid.txt' with size:  8.82kb
   submitting 69samples for 'littlemermaid'
...complete!
df = pd.DataFrame()
# for k,v in d.iteritems():
for k,v in sorted(d.iteritems()):  # sort to ensure dataframe is defined bylongest sequence, which happens to be Aladdin
    df[k] =pd.Series(v)  # keys -> columns; rows-> columns
print(len(df))
df.head(5)  #inspect the first 5 rows...looks OK?
143
Out[12]: