Source Code for Module star

  1  import sys 
  2  from re import match 
  3  from string import split 
  4   
  5 -class star: 
  6 -        def __init__(self): 
  7                  "Class to extract model-free data from the STAR formatted mfout file." 
  8   
  9   
 10 -        def extract(self, mfout, num_res, sse_lim='0.90', ftest_lim='0.80', large_sse=20, ftest='n'): 
 11                  "Extract the data from the mfout file and Return it as a 2D data structure." 
 12   
 13                  self.mfout = mfout 
 14                  self.num_res = num_res 
 15                  self.sse_lim = sse_lim 
 16                  self.ftest_lim = ftest_lim 
 17                  self.large_sse = large_sse 
 18   
 19                  self.data = [] 
 20                  for i in range(self.num_res): 
 21                          self.data.append({}) 
 22                  self.line_num = 0 
 23   
 24                  if match('n', ftest): 
 25                          # Jump to first line of data. 
 26                          for line in range(len(self.mfout)): 
 27                                  self.row = [[]] 
 28                                  self.row[0] = split(self.mfout[line]) 
 29                                  try: 
 30                                          self.row[0][1] 
 31                                  except IndexError: 
 32                                          continue 
 33                                  if match('S2$', self.row[0][0]) and match('\(\)', self.row[0][1]): 
 34                                          self.line_num = line 
 35                                          break 
 36                          self.get_s2() 
 37                          self.get_s2f() 
 38                          self.get_s2s() 
 39                          self.get_te() 
 40                          self.get_rex() 
 41                          self.get_sse() 
 42   
 43                  if match('y', ftest): 
 44                          # Jump to first line of data. 
 45                          for line in range(len(self.mfout)): 
 46                                  self.row = [[]] 
 47                                  self.row[0] = split(self.mfout[line]) 
 48                                  try: 
 49                                          self.row[0][0] 
 50                                  except IndexError: 
 51                                          continue 
 52                                  if match('data_F_dist', self.row[0][0]): 
 53                                          self.line_num = line 
 54                                          break 
 55                          self.get_ftest() 
 56   
 57                  return self.data 
 58   
 59   
 60 -        def get_ftest(self): 
 61                  self.line_num = self.line_num + 5 
 62                  for i in range(self.num_res): 
 63                          self.row = [[]] 
 64                          self.row[0] = split(self.mfout[self.line_num]) 
 65                          percentile = int(float(self.ftest_lim) * 100 / 5) 
 66                          self.line_num = self.line_num + percentile 
 67                          self.row.append(split(self.mfout[self.line_num])) 
 68                          lines_next_res = 2 + ( 20 - percentile ) 
 69                          self.line_num = self.line_num + lines_next_res 
 70                          self.data[i]['res_num'] = self.row[0][0] 
 71                          self.data[i]['fstat'] = float(self.row[0][1]) 
 72                          self.data[i]['fstat_lim'] = float(self.row[1][1]) 
 73                          if self.data[i]['fstat_lim'] < 1.5: 
 74                                  if self.data[i]['fstat'] > 1.5: 
 75                                          self.data[i]['ftest'] = 1 
 76                                  else: 
 77                                          self.data[i]['ftest'] = 0 
 78                          elif self.data[i]['fstat_lim'] >= 1.5: 
 79                                  if self.data[i]['fstat'] > self.data[i]['fstat_lim']: 
 80                                          self.data[i]['ftest'] = 1 
 81                                  else: 
 82                                          self.data[i]['ftest'] = 0 
 83   
 84   
 85 -        def get_rex(self): 
 86                  self.line_num = self.line_num + self.num_res + 3 
 87                  self.row = [[]] 
 88                  self.row[0] = split(self.mfout[self.line_num]) 
 89                  self.split_rows(self.line_num, self.num_res) 
 90                  for i in range(self.num_res): 
 91                          j = i + 1 
 92                          self.data[i]['rex'] = self.row[j][1] 
 93                          self.data[i]['rex_err'] = self.row[j][5] 
 94   
 95   
 96 -        def get_s2(self): 
 97                  self.split_rows(self.line_num, self.num_res) 
 98                  for i in range(self.num_res): 
 99                          j = i + 1 
100                          self.data[i]['res_num'] = self.row[j][0] 
101                          self.data[i]['s2'] = self.row[j][1] 
102                          self.data[i]['s2_err'] = self.row[j][5] 
103   
104   
105 -        def get_s2f(self): 
106                  self.line_num = self.line_num + self.num_res + 3 
107                  self.row = [[]] 
108                  self.row[0] = split(self.mfout[self.line_num]) 
109                  self.split_rows(self.line_num, self.num_res) 
110                  for i in range(self.num_res): 
111                          j = i + 1 
112                          self.data[i]['s2f'] = self.row[j][1] 
113                          self.data[i]['s2f_err'] = self.row[j][5] 
114   
115   
116 -        def get_s2s(self): 
117                  self.line_num = self.line_num + self.num_res + 3 
118                  self.row = [[]] 
119                  self.row[0] = split(self.mfout[self.line_num]) 
120                  self.split_rows(self.line_num, self.num_res) 
121                  for i in range(self.num_res): 
122                          j = i + 1 
123                          self.data[i]['s2s'] = self.row[j][1] 
124                          self.data[i]['s2s_err'] = self.row[j][5] 
125   
126   
127 -        def get_sse(self): 
128                  self.line_num = self.line_num + self.num_res + 8 
129                  for i in range(self.num_res): 
130                          self.row = [[]] 
131                          self.row[0] = split(self.mfout[self.line_num]) 
132                          percentile = int(float(self.sse_lim) * 100 / 5) 
133                          self.line_num = self.line_num + percentile 
134                          self.row.append(split(self.mfout[self.line_num])) 
135                          lines_next_res = 2 + ( 20 - percentile ) 
136                          self.line_num = self.line_num + lines_next_res 
137                          self.data[i]['sse'] = float(self.row[0][1]) 
138                          self.data[i]['sse_lim'] = float(self.row[1][1]) 
139   
140                          # Chi-squared test. 
141                          if self.data[i]['sse'] <= self.data[i]['sse_lim']: 
142                                  self.data[i]['sse_test'] = 1 
143                          else: 
144                                  self.data[i]['sse_test'] = 0 
145   
146                          # Large SSE test. 
147                          if self.data[i]['sse'] >= self.large_sse: 
148                                  self.data[i]['large_sse'] = 1 
149                          else: 
150                                  self.data[i]['large_sse'] = 0 
151   
152                          # Zero SSE test. 
153                          if self.data[i]['sse'] == 0: 
154                                  self.data[i]['zero_sse'] = 1 
155                          else: 
156                                  self.data[i]['zero_sse'] = 0 
157   
158   
159 -        def get_te(self): 
160                  self.line_num = self.line_num + self.num_res + 3 
161                  self.row = [[]] 
162                  self.row[0] = split(self.mfout[self.line_num]) 
163                  self.split_rows(self.line_num, self.num_res) 
164                  for i in range(self.num_res): 
165                          j = i + 1 
166                          self.data[i]['te'] = self.row[j][1] 
167                          self.data[i]['te_err'] = self.row[j][5] 
168   
169   
170 -        def split_rows(self, line_num, num_lines): 
171                  "Get the next 'num_res' lines after a match." 
172   
173                  for i in range(num_lines): 
174                          j = i + 1 
175                          self.row.append(split(self.mfout[line_num + j])) 
176