def main():
# Read in data from CSV
df = pd.read_csv('PurchaseOrderDetail.csv')
a = Adjacency(df, 'RejectedQty')
a.calcandhtml() #optional parameter value 'Y' for printing
def adjmatrix_eucliddist(self, htmlfilename):
# Find full-D distances between texts
n = euclidean_distances(self.dtm)
# make list of all possible comparisons and result
distarray=[]
for c in combinations(list(range(len(n))), 2):
distarray.append([c[0], c[1], n[c[0],c[1]]])
distarray=np.array(distarray)
names = [os.path.basename(fn).replace('.txt', '') for fn in self.filenames]
Adjacency.createhtml(twodarray=distarray, colnames=names, htmlfilename=htmlfilename, printjson=None, plottitle="Euclidian distance for doc vector pairs")
def adjmatrix_docauthttest(self, htmlfilename):
vect = TfidfVectorizer(tokenizer=self.tokenize, input='filename', stop_words='english')
full = vect.fit_transform(self.filenames).toarray()
listy = list(range(len(self.filenames))) # create list representing each doc for all poss combos
pscoresarray=[]
#for j in range(0,len(combos)):
for c in combinations(listy, 2):
first = c[0] # grabbing all possible doc combos
second = c[1]
p = ttest_ind(full[first],full[second])[1] # grabbing p-value (not t-statistic)
pscoresarray.append([first, second, p])
pscoresarray = np.array(pscoresarray)
names = [os.path.basename(fn).replace('.txt', '') for fn in self.filenames]
Adjacency.createhtml(twodarray=pscoresarray, colnames=names, htmlfilename=htmlfilename, printjson=None, plottitle="P-value for document vector pairs")