def make_csv_allData(): # code for making the data # create the master dictionary - key is "96" of the year, and value is the dictionary master_dictionary = allYears_listData_dict() k_years = ["96", "97", "98", "99", "00", "01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12", "13", "14"] # test to see whats in master_dicitonary # pprint.pprint(master_dictionary[k_years[0]]) # returns a dictionary of lists *salary contains upl df_list = [] for y in range(len(k_years)): year_data = master_dictionary[k_years[y]] df = df_name_salary_position(k_years[y], True) # check to see if all the lists are the same lengths: year_list = [] if (len(year_data["salary_list"]) == len(year_data["employee_list"]) and len(year_data["position_list"])): year_str = k_years[y] if (int(year_str)<20): # will have to change after 2020! year_str = "20" + year_str else: year_str = "19" + year_str # print year_str year_list = [year_str] * len(year_data["salary_list"]) # pprint.pprint(year_list) # add the new column of the data to dataframe of name, position, salary df["Year"] = year_list df_list.append(df) # made a list of the data frame! time to concatonate it df_allData = pd.concat(df_list) # pprint.pprint(df_allData) # Make a csv of all the data! df_allData.to_csv(path_or_buf="uvm_employee_salary_data_1994-2014.csv", index=False, columns = ["Year", "Name", "Position", "Salary"])
def boxplot_salary_allYears():
# make the master dictionary of all the data
master = allYears_listData_dict()
# make a dataframe of all the salaries for a year, for all the data
df = df_allYears_salary(master)
plt.figure()
df.boxplot(return_type='axes')
## add title and label axis
plt.ylabel('Salary (USD)')
plt.xlabel("School Year")
plt.title("Distribution of UVM employee salary from 1996 - 2014")
plt.show(block=True) # this is code is needed if run outside of canopy
def boxplot_salary_allYears():
# make the master dictionary of all the data
master = allYears_listData_dict()
# make a dataframe of all the salaries for a year, for all the data
df = df_allYears_salary(master)
plt.figure()
df.boxplot(return_type='axes')
## add title and label axis
plt.ylabel('Salary (USD)')
plt.xlabel("School Year")
plt.title("Distribution of UVM employee salary from 1996 - 2014")
plt.show(block=True) # this is code is needed if run outside of canopy
def make_csv_allData():
# code for making the data
# create the master dictionary - key is "96" of the year, and value is the dictionary
master_dictionary = allYears_listData_dict()
k_years = [
"96", "97", "98", "99", "00", "01", "02", "03", "04", "05", "06", "07",
"08", "09", "10", "11", "12", "13", "14"
]
# test to see whats in master_dicitonary
# pprint.pprint(master_dictionary[k_years[0]]) # returns a dictionary of lists *salary contains upl
df_list = []
for y in range(len(k_years)):
year_data = master_dictionary[k_years[y]]
df = df_name_salary_position(k_years[y], True)
# check to see if all the lists are the same lengths:
year_list = []
if (len(year_data["salary_list"]) == len(year_data["employee_list"])
and len(year_data["position_list"])):
year_str = k_years[y]
if (int(year_str) < 20): # will have to change after 2020!
year_str = "20" + year_str
else:
year_str = "19" + year_str
# print year_str
year_list = [year_str] * len(year_data["salary_list"])
# pprint.pprint(year_list)
# add the new column of the data to dataframe of name, position, salary
df["Year"] = year_list
df_list.append(df)
# made a list of the data frame! time to concatonate it
df_allData = pd.concat(df_list)
# pprint.pprint(df_allData)
# Make a csv of all the data!
df_allData.to_csv(path_or_buf="uvm_employee_salary_data_1994-2014.csv",
index=False,
columns=["Year", "Name", "Position", "Salary"])
##### IMPORT STATEMENTS: #####
from allYears_listData_dict import allYears_listData_dict
from df_allYears_salary import df_allYears_salary
import pandas as pd
import pprint
pd.set_option('max_colwidth',
30) # This is so all the columns can show on my mac
# TEMPORARY ##################################
# make a local reference of the master dictionary of all the data
master = allYears_listData_dict()
def get_outliers(year_str, master_dict):
# # make a local reference of the master dictionary of all the data
# master = allYears_listData_dict()
# #make the complete dataframe of all years
df_allSalary = df_allYears_salary(master_dict)
# Find out what the upper bound for top outliers is:
std = df_allSalary.loc[:, year_str].std()
mean = df_allSalary.loc[:, year_str].mean()
upper_bound = mean + (2 * std)
# making a copy
# df_copy = df_allSalary.loc[:,year_str].copy()
# df_copy = [df_copy > upper_bound]
# print df_copy
# Initialize variables for outliers
index_outliers = [] # collects the index of outlier
salary_outliers = [] #gets the float salary of outliers
def df_avgSalary_position(year_str, sort_boolean):
# create a local All_Data_Dict
data = allYears_listData_dict()
### temporary lists ####
index_hits = []
salary_float = data[year_str]["salary_float"]
position_list = data[year_str]["position_list"]
employee_list = data[year_str]["employee_list"] #for validation purpose!!!
#set that contains a unique position
unique_pos_set = set(position_list) #makes
## Backbone of a potential dataframe
unique_pos_list = []
sum_salary = []
index_employees = []
avg_salary = []
paid_employees_count = []
# convert the set data to a a list
while (len(unique_pos_set) !=
0): # checks to see if the unique_positions is not empty
popped_off = unique_pos_set.pop()
unique_pos_list.append(popped_off)
#### Loop through all the positions in the list
### see what indexes each employee matches to
for i in range(len(unique_pos_list)):
position_name = unique_pos_list[i]
index_employees_matches = []
for j in range(len(position_list)):
if (position_list[j] == position_name):
index_employees_matches.append(j)
else:
pass
index_employees.append(index_employees_matches)
# go through the list again, and add the sum salary for each list
for i in range(len(unique_pos_list)):
#initialize the total salary
total_salary = 0
unpaid_leave = 0
for k in range(len(index_employees[i])):
#index_employee[k]
salary_index = index_employees[i][k]
try:
total_salary += salary_float[salary_index]
except:
unpaid_leave += 1
sum_salary.append({"total": total_salary, "upl": unpaid_leave})
# go through the list again, and add the sum salary for each list
for i in range(len(unique_pos_list)):
total_salary = sum_salary[i]["total"]
# total paid employees is the number of employees minus unpaid
total_employees = len(index_employees[i]) - sum_salary[i]["upl"]
if (total_employees <= 0):
average_salary = 0
else:
average_salary = total_salary / total_employees
# avg_salary.append(average_salary)
avg_salary.append(
'{:20,.2f}'.format(average_salary)
) ### THIS IS FOR FORMATED Version, can't get sorted!
# avg_salary.append(average_salary)
paid_employees_count.append(total_employees)
# avg_salary.append(format(average_salary, ".2"))
# # Create a dataframe!!
data = zip(unique_pos_list, avg_salary, paid_employees_count)
df = pd.DataFrame(
data,
columns=["Employee_Position", "Average_Salary", "Number_of_Employees"])
if (sort_boolean):
df = df.sort(["Average_Salary"], ascending=False)
return df
# if (sort_boolean):
# df.sort(["Average Salary"], ascending=False)
# return df
# ###### CALL FUNCTION / TESTING #####################
# b = df_avgSalary_position("14", True)
# print b
##### IMPORT STATEMENTS: #####
from allYears_listData_dict import allYears_listData_dict
from df_allYears_salary import df_allYears_salary
import pandas as pd
import pprint
pd.set_option('max_colwidth', 30) # This is so all the columns can show on my mac
# TEMPORARY ##################################
# make a local reference of the master dictionary of all the data
master = allYears_listData_dict()
def get_outliers(year_str, master_dict):
# # make a local reference of the master dictionary of all the data
# master = allYears_listData_dict()
# #make the complete dataframe of all years
df_allSalary= df_allYears_salary(master_dict)
# Find out what the upper bound for top outliers is:
std = df_allSalary.loc[:, year_str].std()
mean = df_allSalary.loc[:, year_str].mean()
upper_bound = mean + (2*std)
# making a copy
# df_copy = df_allSalary.loc[:,year_str].copy()
# df_copy = [df_copy > upper_bound]
# print df_copy
# Initialize variables for outliers
index_outliers = [] # collects the index of outlier
salary_outliers = [] #gets the float salary of outliers
def df_name_salary_position(year_str, sort_boolean):
# create a local All_Data_Dict
data = allYears_listData_dict()
### DECLARING LISTS ####
#describes the hits of the unpaid leave employees
index_hits = []
salary_float = data[year_str]["salary_float"]
salary_list = data[year_str]["salary_list"]
position_list = data[year_str]["position_list"]
employee_list = data[year_str]["employee_list"]
########### DEBUGGING ############
if ((len(salary_float) == len(position_list)) and len(position_list) == len(employee_list)):
print "all incoming lists are the same length"
else:
print len(salary_float)
print len(position_list)
print len(employee_list)
########## DEBUGGING ######
# "06"
# Debugging .... there is no Carr,Frances!!!!
# for i in range(len(employee_list)):
# if ("Carr" in employee_list[i]):
# print employee_list[i]
# Fixed Yields:
# Carr,Elizabeth Anne
# Carr,Frances Eileen
# Carr,Jacqueline B.
# Carr,Jeanine M.
# Devoid,Rick Carroll
# Honeman,Carrie Ann
# Previous yielded this below:
# Carr,Elizabeth Anne
# Carr,Jeanine M.
# Carrard,Philippe
# Carrigan,Linda Jean
# Carris,Marschelle R.
# Carroll Higgins,Linda Joan
# Carroll,John A.
# Clough,Carrie Mae
# Honeman,Carrie Ann
# Lewin,Carroll
# MISSING PEOPLE:
# 'Carr,Frances Eileen',
# 'Carr,Jacqueline B.',
## DEBUGGING:
# print len(salary_float)
# print len(position_list)
# print len(employee_list)
# check_list = [1,100,500,1000,2000]
# for i in range(len(check_list)):
# index = check_list[i]
# print ("******************")
# print employee_list[index]
# print salary_float[index]
# print position_list[index]
# #these will be the copies of the original lists, but without upl employees
e_list = []
p_list = []
s_float = []
s_list = []
index_hits = []
## Take care of the UPL salary option ###
for i in range(len(salary_float)):
if (salary_float[i] != ""):
pass
# salary_float[i] = '{:20,.2f}'.format(salary_float[i])
else:
index_hits.append(i)
salary_float[i] = 0
for j in range(len(employee_list)):
if (j in index_hits):
pass
else:
# Original code #########
# e_list.append(employee_list[j])
# p_list.append(position_list[j])
# s_float.append(salary_float[j])
##########################
try:
e_list.append(employee_list[j])
p_list.append(position_list[j])
s_list.append(salary_list[j])
s_float.append(salary_float[j])
except:
print j
# # Create a dataframe!!
# data = zip(e_list, p_list, s_float)
data = zip(employee_list, position_list, salary_float)
df = pd.DataFrame(data, columns=["Name", "Position", "Salary"])
if (sort_boolean):
df = df.sort(["Salary"], ascending=False)
return df