def prepareDBHeaderRow(beer):
headers = []
for col in beer.keys():
if col != "Review Text":
headers.append(col)
for cat_type in getBeerWordCategories().keys():
for col in getBeerWordCategories()[cat_type]:
headers.append(col)
headers.append("Total Count")
return headers
def getBeerWordColumns(csv_filename):
beer_word_categories = getBeerWordCategories()
with open(csv_filename, "rU") as csvfile:
csvreader = csv.reader(csvfile)
header_row = csvreader.next()
for cat_type in beer_word_categories.keys():
for category in beer_word_categories[cat_type]:
beer_word_categories[cat_type][category] = header_row.index(category)
return beer_word_categories
def prepareDBRow(beer):
row = []
for col in beer.keys():
if col != "Review Text":
row.append(beer[col])
total_beer_words = 0
beer_word_counts = countBeerWordsInText(beer["Review Text"])
for cat_type in ["scaled", "binary"]:
categories = getBeerWordCategories()[cat_type]
for category in categories.keys():
words_in_category = beer_word_counts[cat_type][category]
row.append(words_in_category)
total_beer_words += words_in_category
row.append(total_beer_words)
return row
def getCategoryAvgs(csv_filename):
category_columns = getBeerWordColumns(csv_filename)
category_totals = getBeerWordCategories()
num_beers = 0
with open(csv_filename, "rU") as csvfile:
csvreader = csv.reader(csvfile)
csvreader.next()
for row in csvreader:
num_beers += 1
for cat_type in category_columns.keys():
for category in category_columns[cat_type].keys():
cat_count = row[category_columns[cat_type][category]]
total_count = row[len(row) - 1]
category_totals[cat_type][category] += float(cat_count) / float(total_count)
for cat_type in category_totals.keys():
for category in category_totals[cat_type].keys():
print category + ": " + str(category_totals[cat_type][category])
category_totals[cat_type][category] = category_totals[cat_type][category] / num_beers
print "num beers: " + str(num_beers)
return category_totals
