def get_headers_with_cols(cols_to_include):
headers = gd.get_headers()
final = []
for x in range(len(headers)):
if x in cols_to_include:
final.append(headers[x])
return final
def change_to_list_of_lists(list_of_dicts):
headers = gd.get_headers()
final = []
for x in range(len(list_of_dicts)):
final.append([])
for entry in headers:
col = gd.get_data_slice(entry, list_of_dicts)
for y in range(len(list_of_dicts)):
final[y].append(col[y])
return final
def normalize_data():
list_of_dicts = gd.get_data_list_of_dicts()
headers = gd.get_headers()
final = []
for y in range(len(headers)):
final.append([])
for x in range(len(headers)):
col = gd.get_data_slice(headers[x], list_of_dicts)
colFloat = convert_colFloat(col)
final[x].append(np.std(colFloat))
final[x].append(np.mean(colFloat))
return final
def cleaned_headers():
headers = gd.get_headers()
new_headers = []
for entry in headers:
final = ""
for i in entry:
if (i == " " or i == "(" or i == ")" or i == "/" or i == "^"):
final = final
else:
final = final + i
print "entry: " + final
new_headers.append(final)
return new_headers
def remove_dup_cols():
list_of_dicts = gd.get_data_list_of_dicts()
headers = gd.get_headers()
cols_2remove = []
for x in range(len(headers)-15):
col1 = gd.get_data_slice(headers[x],list_of_dicts)
col1 = replace_missing(col1)
for y in range(len(headers)-15):
col2 = gd.get_data_slice(headers[y],list_of_dicts)
col2 = replace_missing(col2)
r = find_r(col1,col2)
pairIn = exist_same_pair(cols_2remove, x, y)
if r>=.99 and r<=1.002 and not x ==y and not pairIn:
cols_2remove.append([y,x, r[0], headers[x], headers[y]])
def clean_headers(headers):
all_headers = gd.get_headers()
new_headers = []
for entry in headers:
final = ""
for i in entry:
if (i == " "):
final = final
else:
final = final + i
print "entry: " + final
new_headers.append(final)
print new_headers
return new_headers
def create_rows_list_of_lists_without_cols(list_of_dicts, cols_to_exclude):
headers = gd.get_headers()
final = []
for x in range(len(list_of_dicts)):
final.append([])
counter = 0
for x in range(len(headers)):
if not x in cols_to_exclude:
col = gd.get_data_slice(headers[x], list_of_dicts)
avg = average_available_values(col)
cleanedCol = gd.get_data_slice_replace(headers[x], list_of_dicts, avg)
counter = 0
for entry in cleanedCol:
final[counter].append(entry)
counter += 1
return final
import get_data as gd
headers_clean = gd.get_headers()
list_of_dicts = gd.get_data_list_of_dicts()
new_headers = []
for h in headers_clean:
h = h.split(",")
if not " Error" in h and not "" in h:
new_headers.append(",".join(h))
final = []
for entry in list_of_dicts:
temp = {}
for header in new_headers:
temp[header] = entry[header]
final.append(temp)
filename = "noError.csv"
headers = new_headers
gd.write_data_dicts(filename, headers, final)
import get_data as gd
list_of_dicts = gd.get_data_list_of_dicts()
final = []
for entry in list_of_dicts:
if entry["Transcript"] != "":
final.append(entry)
filename = "justTranscripts.csv"
headers = gd.get_headers()
gd.write_data_dicts(filename, headers, final)
import get_data as gd
import get_data2 as gd2
import get_data3 as gd3
list_of_dicts = gd.get_data_list_of_dicts()
full = gd2.get_data_list_of_dicts()
full_headers = gd2.get_headers()
headers = gd.get_headers()
headers_income = gd3.get_headers()
codes = {}
full_clean = []
final_headers = []
for h in headers:
h = h.split(" - ")
code = h[0]
try:
name = h[1]
codes[code] = name
except:
print h
for h2 in headers_income:
h2 = h2.split(" - ")
code = h2[0]
try:
if not "Error" in h2[1]:
name = h2[1]
codes[code] = name
except:
import get_data as gd
headers_clean = gd.get_headers()
list_of_dicts = gd.get_data_list_of_dicts()
new_headers = []
for h in headers_clean:
h = h.split(",")
if not " Error" in h and not "" in h:
new_headers.append(",".join(h))
final = []
for entry in list_of_dicts:
temp = {}
for header in new_headers:
temp[header] = entry[header]
final.append(temp)
filename = "noError.csv"
headers = new_headers
gd.write_data_dicts(filename,headers,final)
