def clioindex(self): self.handles = self.getindexpid() storage = Storage(self.database) if self.handles: self.hquery = storage.formdatasetquery(self.handles,'') self.datainfo = storage.readdatasets(json.loads(self.hquery)) self.csvio = StringIO(str(self.datainfo[0]['csvframe'])) self.data = pd.read_csv(self.csvio, sep='\t', dtype='unicode',quoting=csv.QUOTE_NONE) self.columns = [] for item in self.data.columns: self.col = re.sub(r"\"", "", item) self.columns.append(self.col) self.data.columns = self.columns self.storeddata = storage.readdatasets('') self.linking = {} for item in self.storeddata: try: self.linking[item['title']] = item['handle'] except: skip = 'yes' self.data['handle'] = '' for row in self.data.index: title = self.data.ix[row]['Name'] uid = self.data.ix[row]['ID'] try: self.data.ix[row]['handle'] = self.linking[title] self.links[uid] = self.linking[title] except: self.data.ix[row]['handle'] = '' self.data = self.data.drop('ID', axis=1) return self.data
def retrievedatasets(self, handles): self.storeddata = {} storage = Storage(self.database) if handles: self.hquery = storage.formdatasetquery(handles,'') self.datainfo = storage.readdatasets(json.loads(self.hquery)) for self.item in self.datainfo: self.csvio = StringIO(str(self.item['csvframe'])) self.data = pd.read_csv(self.csvio, sep='\t', dtype='unicode',quoting=csv.QUOTE_NONE) self.columns = [] for itemcol in self.data.columns: self.col = re.sub(r"\"", "", itemcol) self.columns.append(self.col) self.data.columns = self.columns self.storeddata[self.item['handle']] = self.data return self.storeddata