SalGuide 3.0 - Final Notebook¶
Run cells sequentially - Enjoy the program!¶
Nabieu Kamara, Research and Testing, nabieu.kamara@gmail.com
Joshua May, Project Management, jmay1@terpmail.umd.edu
Ian Dopsch, Research and Analysis, idopsch@terpmail.umd.edu
Ezenwa Ogbechie, Research and Testing, Ogbechieezenwa@yahoo.com
In [1]:
import pandas as pd # Importing
import numpy as np # All Required
import matplotlib.pyplot as plt # Modules
%matplotlib inline
#--------------------------------------------------------------------------------------------------------------------------
fn = pd.read_csv("C:/Users/JoshW/Desktop/Programming/SalGuide/SalMaster.csv")# Reading
fn.dropna(inplace = True) # Sorting
fn["Department"]= fn["Department"].str.split("-", n = -1, expand = True) # And
fn["Department"]= fn["Department"].str.split(",", n = -1, expand = True) # Cleaning
fn.sort_values(['Last'], ascending=True) # New
fn["First"] = fn.First.str[0:1] # Dataframe
#----------------------------------------------------------------------------------------------------------------------------
#This block intended to give some basic understanding of data
p = fn.Department.value_counts().count() # Assigning Count for --
print('\nThere are',p,'different departments') # and displaying Department count
t = fn.Title.value_counts().count() # Assignging count for --
print('\nThere are',t,'different job titles') # and displaying Job Title count
#----------------------------------------------------------------------------------------------------------------------------
# A This block (for some reason) creates a new dataframe
# B but serves to convert Salary to floating integers
# C and remove hourly workers
# D Sorts new dataframe by descending salary
# E And resets the index, while dropping the original
# F Then sets the index to start at 1 (instead of 0)
# G Oh yeah, and we need to make title all caps for a function later
common_title = fn # A
common_title['Salary'] = common_title[common_title.columns[5]].replace('[\$,]', '', regex=True).astype(float) # B
pd.options.display.float_format = '${:,.2f}'.format
common_title = common_title.loc[common_title['Salary'] > 20000] # C
common_title = common_title.sort_values('Salary',ascending=False) # D
common_title.reset_index(drop=True, inplace=True) # E
common_title.index += 1 # F
common_title['Title'] = common_title['Title'].str.upper() # G
common_title.head(50)
Out[1]:
A deeper look at salary data for each year¶
Dataframes created for each year
5 number summaries for each year are produced
Then they are plotted in box & whisker plots
In [2]:
y_all_mean = common_title['Salary'].mean() # Dataframes created for individual years
y_all_x = common_title.loc[common_title['Salary'] > 20000]
y_all_min = y_all_x['Salary'].min()
y_all_med = common_title['Salary'].median()
y_all_max = common_title['Salary'].max()
y_all_1q = (y_all_min + y_all_med)/2
y_all_3q = (y_all_max + y_all_med)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
year17 = common_title.loc[common_title['Year'] == 2017] #2017 snip
y17mean = year17['Salary'].mean()
y17x = year17.loc[year17['Salary'] > 2000]
y17min = y17x['Salary'].min()
y17med = year17['Salary'].median()
y17max = year17['Salary'].max()
y17_1q = (y17min + y17med)/2
y17_3q = (y17max + y17med)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
year16 = common_title.loc[common_title['Year'] == 2016] #2016 snip
y16x = year16.loc[year16['Salary'] > 20000]
y16min = y16x['Salary'].min()
y16mean = year16['Salary'].mean()
y16med = year16['Salary'].median()
y16max = year16['Salary'].max()
y16_1q = (y16min + y16med)/2
y16_3q = (y16max + y16med)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
year15 = common_title.loc[common_title['Year'] == 2015] #2015 snip
y15x = year15.loc[year15['Salary'] > 20000]
y15min = y15x['Salary'].min()
y15mean = year15['Salary'].mean()
y15med = year15['Salary'].median()
y15max = year15['Salary'].max()
y15_1q = (y15min + y15med)/2
y15_3q = (y15max + y15med)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
year14 = common_title.loc[common_title['Year'] == 2014] #2014 snip
y14x = year14.loc[year14['Salary'] > 20000]
y14min = y14x['Salary'].min()
y14mean = year14['Salary'].mean()
y14med = year14['Salary'].median()
y14max = year14['Salary'].max()
y14_1q = (y14min + y14med)/2
y14_3q = (y14max + y14med)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
year13 = common_title.loc[common_title['Year'] == 2013] #2013 snip
y13x = year13.loc[year13['Salary'] > 20000]
y13min = y17x['Salary'].min()
y13mean = year13['Salary'].mean()
y13med = year13['Salary'].median()
y13max = year13['Salary'].max()
y13_1q = (y13min + y13med)/2
y13_3q = (y13max + y13med)/2
#--------------------------------------------------------------------------------------------------------------------------------
all_summ = y_all_min, y_all_1q, y_all_med, y_all_3q, y_all_max # Now that we have all the necessary assignments
y13_summ = y13min, y13_1q, y13med, y13_3q, y13max # We need to create assignments to store them together
y14_summ = y14min, y14_1q, y14med, y14_3q, y14max
y15_summ = y15min, y15_1q, y15med, y17_3q, y15max
y16_summ = y16min, y16_1q, y16med, y16_3q, y16max
y17_summ = y17min, y17_1q, y17med, y17_3q, y17max
#--------------------------------------------------------------------------------------------------------------------------------
fig, axs = plt.subplots(2, 3) # This line needed for separate plots
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
axs[0, 0].boxplot(all_summ, 0, '') # And here we set up a plot for each year
axs[0, 0].set_title("All Years") # With each given a space to occupy within 6 separate plots
axs[0, 1].boxplot(y13_summ, 0, '')
axs[0, 1].set_title("2013")
axs[0, 2].boxplot(y14_summ, 0, '')
axs[0, 2].set_title("2014")
axs[1, 0].boxplot(y15_summ, 0, '')
axs[1, 0].set_title("2015")
axs[1, 1].boxplot(y16_summ, 0, '')
axs[1, 1].set_title("2016")
axs[1, 2].boxplot(y17_summ, 0, '')
axs[1, 2].set_title("2017")
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=3) # Almost ready for plotting!
# But first we need to adust space
# So we do so here
# - - - - - - - - - - - - - - - - - - - - - - - - -
print('\n',
'The average salary at UMD for all years was','$%0.2f'%y_all_mean,'\n\n',
'The average salary at UMD for 2013 was','$%0.2f'%y13mean,'\n',
'The average salary at UMD for 2014 was','$%0.2f'%y14mean,'\n',
'The average salary at UMD for 2015 was','$%0.2f'%y15mean,'\n',
'The average salary at UMD for 2016 was','$%0.2f'%y16mean,'\n',
'The average salary at UMD for 2017 was','$%0.2f'%y17mean,'\n')
In [10]:
def scatter(data):
salary = data['Salary']
department = data['Department']
plt.figure(figsize=(8,6))
plt.scatter(salary, department)
year = data['Year'].unique()
yr = list()
for i in year:
i = int(i)
yr.append(i)
yr.sort()
text = 'Salaries vs Department',yr
plt.title(text)
plt.ylabel('Department')
plt.xlabel('Salary')
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=5)
plt.show()
In [11]:
inp = input('Which year or years are interested in?\n(Individual year is reccomended.)\n Please, separate values by comma.\n\n') # This block takes user input
inp = inp.lower() # Makes each letter lowercase
inp = inp.split(",") # Splits it by comma to separate years
y = len(inp) # And assigns a variable to the length of a split list
year = pd.DataFrame(columns = ['Year','Last', 'First', 'Department', 'Title', 'Salary']) # This dataframe is created to house
# data for a multiyear frame
#---------------------------------------------------------------------------------------------------------------------------------------------------------------
# The input serves as fuel to this for statement
for i in inp: # This lengthy block is written to separate the master dataframe by
i = str(i) # User submitted years
i = i.lstrip() # Several if statements are used to determine the years of the input by:
if i == 'all' or i == 'all years': # Number of [i]tems
year = common_title # And building upon itself as it gets hits
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if i == '2017' or i == '17':
if y > 1:
year = pd.concat([year, year17])
p = '2017'
else:
year = year17 # 2017 snip
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if i == '2016' or i == '16':
if y > 1:
year = pd.concat([year, year16])
else:
year = year16 # 2016 snip
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if i == '2015' or i == '15':
if y > 1:
year = pd.concat([year, year15])
else:
year = year15 # 2015 snip
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if i == '2014' or i == '14':
if y > 1:
year = pd.concat([year, year14])
else:
year = year14 # 2014 snip
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if i == '2013' or i == '13':
if y > 1:
year = pd.concat([year, year13])
else:
year = year13 # 2013 snip
continue
else:
print("\n","Look, nothing personal, but we didn't write this script with a try/except\n",
"and you cannot follow directions...\n",
"So this is where this ends, and you need to run this cell again\n\n",
"PEACE!")
break
#-----------------------------------------------------------------------------------------------------------------------------------------------------------
year = year.sort_values('Year', ascending = True) #This sort occurs to order the dataframe so the year output is chronological
yn = year['Year'].unique()
year = year.sort_values('Salary', ascending = False)
print(yn) #This output verifies that the input was properly converted to the specified years
scatter(year)
The next block is used to store functions that will be used in further analysis¶
Functions include whisker_func(data), pg_break(), yr_quick_view(year), and spec_quick_view(data)
In [12]:
#\____________/\____________/\____________/\____________/\____________/\____________/\____________/\____________/\____________/--
#--\________/----\________/----\________/----\________/----\________/----\________/----\________/----\________/----\________/----
#----\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/------
#------\/------------\/------------\/------------\/------------\/------------\/------------\/------------\/------------\/--------
def whisker_func(data, yn, inp):
data = data.sort_values('Year', ascending = True)
ymin = data['Salary'].min()
ymean = data['Salary'].mean()
ymed = data['Salary'].median()
ymax = data['Salary'].max()
y_1q = (ymin + ymed)/2
y_3q = (ymax + ymed)/2
summ = ymin, y_1q, ymed, y_3q, ymax
yn = data['Year'].unique()
title = "Box and Whisker Plot for",str(yn)
fig, ax = plt.subplots()
ax.boxplot(summ)
blanky = list()
for i in yn:
blanky.append(i)
fig.align_ylabels(axs[-2:, ])
text = 'Salary for',blanky
ax.set_ylabel(text)
ax.set_xlabel(inp)
#\____________/\____________/\____________/\____________/\____________/\____________/\____________/\____________/\____________/--
#--\________/----\________/----\________/----\________/----\________/----\________/----\________/----\________/----\________/----
#----\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/------
#------\/------------\/------------\/------------\/------------\/------------\/------------\/------------\/------------\/--------
def yr_quick_view(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
top100 = year.head(100)
avg100 = top100['Salary'].mean()
min100 = top100['Salary'].min()
med100 = top100['Salary'].median()
max100 = top100['Salary'].max()
yr_1q100 = (min100 + med100)/2
yr_3q100 = (max100 + med100)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
top250 = year.head(250)
avg250 = top250['Salary'].mean()
min250 = top250['Salary'].min()
med250 = top250['Salary'].median()
max250 = top250['Salary'].max()
yr_1q250 = (min250 + med250)/2
yr_3q250 = (max250 + med250)/2
# - - - - - - - - - - - - - - - - - - - - - - - - -
top500 = year.head(500)
avg500 = top500['Salary'].mean()
min500 = top500['Salary'].min()
med500 = top500['Salary'].median()
max500 = top500['Salary'].max()
yr_1q500 = (min500 + med500)/2
yr_3q500 = (max500 + med500)/2
#--------------------------------------------------------------------------------------------------------------------------------
t10_summ = min10, yr_1q10, med10, yr_3q10, max10 # Now that we have all the necessary assignments
t25_summ = min25, yr_1q25, med25, yr_3q25, max25 # We need to create assignments to store them together
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
t100_summ = min100, yr_1q100, med100, yr_1q100, max100
t250_summ = min250, yr_1q250, med250, yr_1q250, max250
t500_summ = min500, yr_1q500, med500, yr_1q500, max500
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(2, 3) # This line needed for separate plots
# - - - - - - - - - - - - - - - - - - - - - - - - -
# - - - - - - - - - - - - - - - - - - - - - - - - -
axs[0, 0].boxplot(t10_summ, 0, '') # And here we set up a plot for each year
axs[0, 0].set_title("Top 10 Salaries") # With each given a space to occupy within 6 separate plots
axs[0, 1].boxplot(t25_summ, 0, '')
axs[0, 1].set_title("Top 25 Salaries")
axs[0, 2].boxplot(t50_summ, 0, '')
axs[0, 2].set_title("Top 50 Salaries")
axs[1, 0].boxplot(t100_summ, 0, '')
axs[1, 0].set_title("Top 100 Salaries")
axs[1, 1].boxplot(t250_summ, 0, '')
axs[1, 1].set_title("Top 250 Salaries")
axs[1, 2].boxplot(t500_summ, 0, '')
axs[1, 2].set_title("Top 500 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=3)
#\____________/\____________/\____________/\____________/\____________/\____________/\____________/\____________/\____________/--
#--\________/----\________/----\________/----\________/----\________/----\________/----\________/----\________/----\________/----
#----\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/--------\____/------
#------\/------------\/------------\/------------\/------------\/------------\/------------\/------------\/------------\/--------
Creating multiple plotting functions to be used in if statements based parsed dataframes¶
In [13]:
def spec_quick_500(year):
tot_emp = year.Year.value_counts().count()
meany = year['Salary'].mean()
mini = year['Salary'].min()
medi = year['Salary'].median()
maxi = year['Salary'].max()
yr_1q_tot = (mini + medi)/2
yr_3q_tot = (maxi + medi)/2
tot_summ = mini, yr_1q_tot, medi, yr_3q_tot, maxi
#--------------------------------------------------------------------------------------------------------------------------------
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
top100 = year.head(100)
avg100 = top100['Salary'].mean()
min100 = top100['Salary'].min()
med100 = top100['Salary'].median()
max100 = top100['Salary'].max()
yr_1q100 = (min100 + med100)/2
yr_3q100 = (max100 + med100)/2
t100_summ = min100, yr_1q100, med100, yr_1q100, max100
# - - - - - - - - - - - - - - - - - - - - - - - - -
top250 = year.head(250)
avg250 = top250['Salary'].mean()
min250 = top250['Salary'].min()
med250 = top250['Salary'].median()
max250 = top250['Salary'].max()
yr_1q250 = (min250 + med250)/2
yr_3q250 = (max250 + med250)/2
t250_summ = min250, yr_1q250, med250, yr_1q250, max250
# - - - - - - - - - - - - - - - - - - - - - - - - -
top500 = year.head(500)
avg500 = top500['Salary'].mean()
min500 = top500['Salary'].min()
med500 = top500['Salary'].median()
max500 = top500['Salary'].max()
yr_1q500 = (min500 + med500)/2
yr_3q500 = (max500 + med500)/2
t500_summ = min500, yr_1q500, med500, yr_1q500, max500
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(2, 3) # This line needed for separate plots
axs[0, 0].boxplot(t10_summ, 0, '') # And here we set up a plot for each year
axs[0, 0].set_title("Top 10 Salaries") # With each given a space to occupy within 6 separate plots
axs[0, 1].boxplot(t25_summ, 0, '')
axs[0, 1].set_title("Top 25 Salaries")
axs[0, 2].boxplot(t50_summ, 0, '')
axs[0, 2].set_title("Top 50 Salaries")
axs[1, 0].boxplot(t100_summ, 0, '')
axs[1, 0].set_title("Top 100 Salaries")
axs[1, 1].boxplot(t250_summ, 0, '')
axs[1, 1].set_title("Top 250 Salaries")
axs[1, 2].boxplot(t500_summ, 0, '')
axs[1, 2].set_title("Top 500 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=3)
#--------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_quick_250(year):
tot_emp = year.Year.value_counts().count()
meany = year['Salary'].mean()
mini = year['Salary'].min()
medi = year['Salary'].median()
maxi = year['Salary'].max()
yr_1q_tot = (mini + medi)/2
yr_3q_tot = (maxi + medi)/2
tot_summ = mini, yr_1q_tot, medi, yr_3q_tot, maxi
#--------------------------------------------------------------------------------------------------------------------------------
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
top100 = year.head(100)
avg100 = top100['Salary'].mean()
min100 = top100['Salary'].min()
med100 = top100['Salary'].median()
max100 = top100['Salary'].max()
yr_1q100 = (min100 + med100)/2
yr_3q100 = (max100 + med100)/2
t100_summ = min100, yr_1q100, med100, yr_1q100, max100
# - - - - - - - - - - - - - - - - - - - - - - - - -
top250 = year.head(250)
avg250 = top250['Salary'].mean()
min250 = top250['Salary'].min()
med250 = top250['Salary'].median()
max250 = top250['Salary'].max()
yr_1q250 = (min250 + med250)/2
yr_3q250 = (max250 + med250)/2
t250_summ = min250, yr_1q250, med250, yr_1q250, max250
fig, axs = plt.subplots(2, 3)
axs[0, 0].boxplot(t10_summ, 0, '')
axs[0, 0].set_title("Top 10 Salaries")
axs[0, 1].boxplot(t25_summ, 0, '')
axs[0, 1].set_title("Top 25 Salaries")
axs[0, 2].boxplot(t50_summ, 0, '')
axs[0, 2].set_title("Top 50 Salaries")
axs[1, 0].boxplot(t100_summ, 0, '')
axs[1, 0].set_title("Top 100 Salaries")
axs[1, 1].boxplot(t250_summ, 0, '')
axs[1, 1].set_title("Top 250 Salaries")
axs[1, 2].boxplot(tot_summ, 0, '')
axs[1, 2].set_title("All Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=.75)
#--------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_quick_100(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
top100 = year.head(100)
avg100 = top100['Salary'].mean()
min100 = top100['Salary'].min()
med100 = top100['Salary'].median()
max100 = top100['Salary'].max()
yr_1q100 = (min100 + med100)/2
yr_3q100 = (max100 + med100)/2
t100_summ = min100, yr_1q100, med100, yr_1q100, max100
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(1, 4)
axs[0].boxplot(t10_summ, 0, '')
axs[0].set_title("Top 10 Salaries")
axs[1].boxplot(t25_summ, 0, '')
axs[1].set_title("Top 25 Salaries")
axs[2].boxplot(t50_summ, 0, '')
axs[2].set_title("Top 50 Salaries")
axs[3].boxplot(t100_summ, 0, '')
axs[3].set_title("Top 100 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=.75)
#--------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_quick_50(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(1, 3)
axs[0].boxplot(t10_summ, 0, '')
axs[0].set_title("Top 10 Salaries")
axs[1].boxplot(t25_summ, 0, '')
axs[1].set_title("Top 25 Salaries")
axs[2].boxplot(t50_summ, 0, '')
axs[2].set_title("Top 50 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=1)
#-------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_quick_25(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(1,2)
axs[0].boxplot(t10_summ, 0, '')
axs[0].set_title("Top 10 Salaries")
axs[1].boxplot(t25_summ, 0, '')
axs[1].set_title("Top 25 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=1)
#----------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_quick_10(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots()
axs.boxplot(t10_summ, 0, '')
axs.set_title("Top 10 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=3)
#-------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_bot_500(year):
tot_emp = year.Year.value_counts().count()
meany = year['Salary'].mean()
mini = year['Salary'].min()
medi = year['Salary'].median()
maxi = year['Salary'].max()
yr_1q_tot = (mini + medi)/2
yr_3q_tot = (maxi + medi)/2
tot_summ = mini, yr_1q_tot, medi, yr_3q_tot, maxi
#--------------------------------------------------------------------------------------------------------------------------------
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
top100 = year.head(100)
avg100 = top100['Salary'].mean()
min100 = top100['Salary'].min()
med100 = top100['Salary'].median()
max100 = top100['Salary'].max()
yr_1q100 = (min100 + med100)/2
yr_3q100 = (max100 + med100)/2
t100_summ = min100, yr_1q100, med100, yr_1q100, max100
# - - - - - - - - - - - - - - - - - - - - - - - - -
top250 = year.head(250)
avg250 = top250['Salary'].mean()
min250 = top250['Salary'].min()
med250 = top250['Salary'].median()
max250 = top250['Salary'].max()
yr_1q250 = (min250 + med250)/2
yr_3q250 = (max250 + med250)/2
t250_summ = min250, yr_1q250, med250, yr_1q250, max250
# - - - - - - - - - - - - - - - - - - - - - - - - -
top500 = year.head(500)
avg500 = top500['Salary'].mean()
min500 = top500['Salary'].min()
med500 = top500['Salary'].median()
max500 = top500['Salary'].max()
yr_1q500 = (min500 + med500)/2
yr_3q500 = (max500 + med500)/2
t500_summ = min500, yr_1q500, med500, yr_1q500, max500
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(2, 3) # This line needed for separate plots
axs[0, 0].boxplot(t10_summ, 0, '') # And here we set up a plot for each year
axs[0, 0].set_title("Bottom 10 Salaries") # With each given a space to occupy within 6 separate plots
axs[0, 1].boxplot(t25_summ, 0, '')
axs[0, 1].set_title("Bottom 25 Salaries")
axs[0, 2].boxplot(t50_summ, 0, '')
axs[0, 2].set_title("Bottom 50 Salaries")
axs[1, 0].boxplot(t100_summ, 0, '')
axs[1, 0].set_title("Bottom 100 Salaries")
axs[1, 1].boxplot(t250_summ, 0, '')
axs[1, 1].set_title("Bottom 250 Salaries")
axs[1, 2].boxplot(t500_summ, 0, '')
axs[1, 2].set_title("Bottom 500 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=3)
#--------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_bot_250(year):
tot_emp = year.Year.value_counts().count()
meany = year['Salary'].mean()
mini = year['Salary'].min()
medi = year['Salary'].median()
maxi = year['Salary'].max()
yr_1q_tot = (mini + medi)/2
yr_3q_tot = (maxi + medi)/2
tot_summ = mini, yr_1q_tot, medi, yr_3q_tot, maxi
#--------------------------------------------------------------------------------------------------------------------------------
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
top100 = year.head(100)
avg100 = top100['Salary'].mean()
min100 = top100['Salary'].min()
med100 = top100['Salary'].median()
max100 = top100['Salary'].max()
yr_1q100 = (min100 + med100)/2
yr_3q100 = (max100 + med100)/2
t100_summ = min100, yr_1q100, med100, yr_1q100, max100
# - - - - - - - - - - - - - - - - - - - - - - - - -
top250 = year.head(250)
avg250 = top250['Salary'].mean()
min250 = top250['Salary'].min()
med250 = top250['Salary'].median()
max250 = top250['Salary'].max()
yr_1q250 = (min250 + med250)/2
yr_3q250 = (max250 + med250)/2
t250_summ = min250, yr_1q250, med250, yr_1q250, max250
fig, axs = plt.subplots(2, 3)
axs[0, 0].boxplot(t10_summ, 0, '')
axs[0, 0].set_title("Bottom 10 Salaries")
axs[0, 1].boxplot(t25_summ, 0, '')
axs[0, 1].set_title("Bottom 25 Salaries")
axs[0, 2].boxplot(t50_summ, 0, '')
axs[0, 2].set_title("Bottom 50 Salaries")
axs[1, 0].boxplot(t100_summ, 0, '')
axs[1, 0].set_title("Bottom 100 Salaries")
axs[1, 1].boxplot(t250_summ, 0, '')
axs[1, 1].set_title("Bottom 250 Salaries")
axs[1, 2].boxplot(tot_summ, 0, '')
axs[1, 2].set_title("All Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=.75)
#--------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_bot_100(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
top100 = year.head(100)
avg100 = top100['Salary'].mean()
min100 = top100['Salary'].min()
med100 = top100['Salary'].median()
max100 = top100['Salary'].max()
yr_1q100 = (min100 + med100)/2
yr_3q100 = (max100 + med100)/2
t100_summ = min100, yr_1q100, med100, yr_1q100, max100
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(1, 4)
axs[0].boxplot(t10_summ, 0, '')
axs[0].set_title("Bottom 10 Salaries")
axs[1].boxplot(t25_summ, 0, '')
axs[1].set_title("Bottom 25 Salaries")
axs[2].boxplot(t50_summ, 0, '')
axs[2].set_title("Bottom 50 Salaries")
axs[3].boxplot(t100_summ, 0, '')
axs[3].set_title("Bottom 100 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=.75)
#--------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_bot_50(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
top50 = year.head(50)
avg50 = top50['Salary'].mean()
min50 = top50['Salary'].min()
med50 = top50['Salary'].median()
max50 = top50['Salary'].max()
yr_1q50 = (min50 + med50)/2
yr_3q50 = (max50 + med50)/2
t50_summ = min50, yr_1q50, med50, yr_3q50, max50
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(1, 3)
axs[0].boxplot(t10_summ, 0, '')
axs[0].set_title("Bottom 10 Salaries")
axs[1].boxplot(t25_summ, 0, '')
axs[1].set_title("Bottom 25 Salaries")
axs[2].boxplot(t50_summ, 0, '')
axs[2].set_title("Bottom 50 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=1)
#-------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_bot_25(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
top25 = year.head(25)
avg25 = top25['Salary'].mean()
min25 = top25['Salary'].min()
med25 = top25['Salary'].median()
max25 = top25['Salary'].max()
yr_1q25 = (min25 + med25)/2
yr_3q25 = (max25 + med25)/2
t25_summ = min25, yr_1q25, med25, yr_3q25, max25
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots(1,2)
axs[0].boxplot(t10_summ, 0, '')
axs[0].set_title("Top 10 Salaries")
axs[1].boxplot(t25_summ, 0, '')
axs[1].set_title("Top 25 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=1)
#----------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
def spec_bot_10(year):
top10 = year.head(10)
avg10 = top10['Salary'].mean()
min10 = top10['Salary'].min()
med10 = top10['Salary'].median()
max10 = top10['Salary'].max()
yr_1q10 = (min10 + med10)/2
yr_3q10 = (max10 + med10)/2
t10_summ = min10, yr_1q10, med10, yr_3q10, max10
# - - - - - - - - - - - - - - - - - - - - - - - - -
fig, axs = plt.subplots()
axs.boxplot(t10_summ, 0, '')
axs.set_title("Top 10 Salaries")
fig.subplots_adjust(left=0.08, right=1.8, bottom=0.05, top=0.9,
hspace=0.4, wspace=3)
#-------------------------------------------------------------------------------------------------------------------------------
#--------------------------------------------------------------------------------------------------------------------------------
Create a function for analysis of 'year' based on department¶
This block creates a function for analyzing 'year' created in block 3. The goal is to craft coding that allows the user to specify what they see based on their want/need. Once completed, it would ideally perform to crunch data as desired and give options for output (Flowchart to come)
In [15]:
def year_plt_dept(year):
#The following code loops through code pertaining to a departmental input response
inp2 = input('Do you want to know about a specific department or various?')
inp2.lower()
if inp2 == 'specific' or inp2 == 'specific department' or inp2 == 'spec' or inp2 == 'specific dept':
depts = year['Department'].value_counts()
print('Different departments with value counts:\n')
print(depts.head(20))
inp3 = input('\nWhich department?\n')
inp3 = inp3.upper()
spec = year.loc[inp3 == year['Department']]
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
d_sal = spec.loc[spec['Salary'] > 20000]
sal_cnt = d_sal['Year'].count() # This variable created to count salary employees
sal_avg = d_sal['Salary'].mean() #Created to average salary wages
print("\nFor", yn,"in the",inp3,"department: \n")
print("There were",sal_cnt,"salary employees.\nThe average salary was",'$%0.2f'% sal_avg,'\n')
#---------------------------------------------------------------------------------------------------------------------------------------
print('\nWould you like to further analyze',inp3,'for',yn,'?\n')
inp4 = input('Yes or no?\n')
inp4.lower()
if inp4 == 'yes' or inp4 == 'y' or inp4 == 'yeah':
if spec['Title'].count() < 1:
print('\nSorry.\nThere were no results.\nGoodbye')
else:
inp5 = input('\nSort high to low(descending) or low to high(ascending) values?\n') #This block sorts 'department' values and .head as specified
inp5.lower()
if inp5 == 'high to low' or inp5 == 'high low' or inp5 == 'h l' or inp5 == 'descending':
inp6 = int(input('How many values would you like to assess?\n(Give an integer value)\n'))
spec = spec.sort_values(['Salary'], ascending=False)
spec = spec.head(inp6)
spec.reset_index(drop=True, inplace=True)
spec.index += 1
spec_avg = spec['Salary'].mean()
spec_min = spec['Salary'].min()
spec_max = spec['Salary'].max()
print('\nFor',yn,'in the',inp3,'department:\n(Pay sorted',inp5,'and top',inp6,'values)\n')
print('The minimum pay was','$%0.2f'%spec_min)
print('The maximum pay was','$%0.2f'%spec_max)
print('The average pay was','$%0.2f'%spec_avg,'\n')
if inp6 > 499:
whisker_func(spec, yn, inp3)
spec_quick_500(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 249 and inp6 < 500:
whisker_func(spec, yn, inp3)
spec_quick_250(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 99 and inp6 < 250:
whisker_func(spec, yn, inp3)
spec_quick_100(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 49 and inp6 < 100:
whisker_func(spec, yn, inp3)
spec_quick_50(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 24 and inp6 < 50:
whisker_func(spec, yn, inp3)
spec_quick_25(spec)
scatter(spec)
print(spec)
if inp6 > 9 and inp6 < 25:
whisker_func(spec, yn, inp3)
spec_quick_10(spec)
scatter(spec)
print(spec)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if inp5 == 'low to high' or inp5 == 'low high' or inp5 == 'l h' or inp5 == 'ascending':
spec = spec.sort_values(['Salary'], ascending=True)
inp6 = int(input('How many values would you like to assess?\n(Give an integer value)\n'))
spec = spec.head(inp6)
spec.reset_index(drop=True, inplace=True)
spec.index += 1
spec_avg = spec['Salary'].mean()
spec_min = spec['Salary'].min()
spec_max = spec['Salary'].max()
print('\nFor',yn,'in the',inp3,'department:\n(Pay sorted',inp5,'and top',inp6,'values)\n')
print('The minimum pay was','$%0.2f'%spec_min)
print('The maximum pay was','$%0.2f'%spec_max)
print('The average pay was','$%0.2f'%spec_avg,'\n')
print(spec)
if inp6 > 499:
whisker_func(spec, yn, inp3)
spec_bot_500(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 249 and inp6 < 500:
whisker_func(spec, yn, inp3)
spec_bot_250(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 99 and inp6 < 250:
whisker_func(spec, yn, inp3)
spec_bot_100(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 49 and inp6 < 100:
whisker_func(spec, yn, inp3)
spec_bot_50(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 24 and inp6 < 50:
whisker_func(spec, yn, inp3)
spec_bot_25(spec)
scatter(spec)
print(spec)
if inp6 > 9 and inp6 < 25:
whisker_func(spec, yn, inp3)
spec_bot_10(spec)
scatter(spec)
print(spec)
if inp4 == 'no' or inp4 == 'n' or inp4 == 'nah':
print('Okay!')
#---------------------------------------------------------------------------------------------------------------------------------------
#The following code loops through code pertaining to a positive departmental summary response
if inp2 == 'various' or inp2 =='multiple':
dep_lis = list()
depts = year['Department'].value_counts()
print('Different departments with value counts:\n',depts.head(20))
inp3 = input('Which departments?\n-----Up to 3-----\n(Separate by comma)\n')
inp3 = inp3.upper()
inp3 = inp3.split(",")
inp3list = list()
for i in inp3:
i = str(i)
i = i.lstrip()
inp3list.append(i)
print(inp3list)
length = len(inp3list)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
x = 0
while x < length:
if x == 0:
key = inp3list[x]
spec = year.loc[key == year['Department']]
x = x + 1
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if x == 1:
key = inp3list[x]
spec2 = year.loc[key == year['Department']]
x = x + 1
clean = pd.concat([spec,spec2])
spec = clean
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if x == 2:
key = inp3list[x]
spec3 = year.loc[key == year['Department']]
x = x + 1
clean = pd.concat([clean, spec3])
spec = clean
continue
#-------------------------------------------------------------------------------------------------------------------------------------
d_sal = spec.loc[spec['Salary'] > 20000] # This variable created to count salary employees
sal_cnt = d_sal['Year'].count() #Created to average salary wages
sal_avg = d_sal['Salary'].mean()
print("\nFor", yn,"in the",inp3list,"department: \n")
print("There were",sal_cnt,"salary employees.\nThe average salary was",'$%0.2f'% sal_avg,'\n')
print(spec)
#---------------------------------------------------------------------------------------------------------------------------------------
#The following code allows the user to specify value sort and .head()
print('\nWould you like to further analyze',inp3list,'for',yn,'?\n')
inp4 = input('Yes or no?\n')
inp4.lower()
if inp4 == 'yes' or inp4 == 'y' or inp4 == 'yeah':
if spec['Title'].count() < 1:
print('\nSorry.\nThere were no results.\nGoodbye')
else:
inp5 = input('Sort high to low(descending) or low to high values(ascending)?\n') #This block sorts 'department' values and .head as specified
inp5.lower()
if inp5 == 'high to low' or inp5 == 'high low' or inp5 == 'h l' or inp5 == 'descending':
inp6 = int(input('How many values would you like to assess?\n(Give an integer value)\n'))
spec = spec.sort_values('Salary', ascending = False)
spec.reset_index(drop=True, inplace=True)
spec.index += 1
spec_avg = spec['Salary'].mean()
spec_min = spec['Salary'].min()
spec_max = spec['Salary'].max()
print('\nFor',yn,'in the',inp3list,'departments:\n(Pay sorted',inp5,'and top',inp6,'values)\n')
print('The minimum pay was','$%0.2f'%spec_min)
print('The maximum pay was','$%0.2f'%spec_max)
print('The average pay was','$%0.2f'%spec_avg,'\n')
spec = spec.head(inp6)
if inp6 > 499:
whisker_func(spec, yn, inp3list)
spec_quick_500(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 249 and inp6 < 500:
whisker_func(spec, yn, inp3list)
spec_quick_250(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 99 and inp6 < 250:
whisker_func(spec, yn, inp3list)
spec_quick_100(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 49 and inp6 < 100:
whisker_func(spec, yn, inp3list)
spec_quick_50(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 24 and inp6 < 50:
whisker_func(spec, yn, inp3list)
spec_quick_25(spec)
scatter(spec)
print(spec)
if inp6 > 9 and inp6 < 25:
whisker_func(spec, yn, inp3list)
spec_quick_10(spec)
scatter(spec)
print(spec)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if inp4 == 'no' or inp4 == 'n' or inp4 == 'nah':
print('Okay!')
In [16]:
def year_plt_title(year):
#The following code loops through code pertaining to a title input response
inp2 = input('Do you want to know about a specific title or various?')
inp2.lower()
#------------------------------------------------------------------------------------------------------------------------------------
if inp2 == 'specific' or inp2 == 'specific title' or inp2 == 'spec' or inp2 == 'specific title':
titles = year['Title'].value_counts()
print('Different titles with value counts:\n')
print(titles.head(20))
inp3 = input('What title?\n')
inp3 = inp3.upper()
spec = year.loc[inp3 == year['Title']]
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
print("\nFor", inp3,"in",yn,": \n")
d_bonus = spec.loc[(spec['Salary'] < 20000)]
bon_cnt = d_bonus['Year'].count() # This variable created to count annual bonuses
bon_avg = d_bonus['Salary'].mean() # Created to give average bonus number
if bon_cnt != 0:
print("There were",bon_cnt,"%s's"% inp3,"with bonuses.\nThe average bonus was","$%0.2f"%bon_avg)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
d_sal = spec.loc[spec['Salary'] > 20000]
sal_cnt = d_sal['Year'].count() # This variable created to count salary employees
sal_avg = d_sal['Salary'].mean() #Created to average salary wages
if sal_cnt != 0:
print("There were",sal_cnt,"salary employees with the title", inp3,".\nThe average salary was",'$%0.2f'% sal_avg,'\n')
#-------------------------------------------------------------------------------------------------------------------------------------------------
print('\nWould you like to further analyze',inp3,'for',yn,'?\n')
inp4 = input('Yes or no?\n')
inp4.lower()
if inp4 == 'yes' or inp4 == 'y' or inp4 == 'yeah':
if spec['Title'].count() < 1:
print('\nSorry.\nThere were no results.\nGoodbye')
else:
inp5 = input('Sort high to low(descending) or low to high values?(ascending)\n') #This block sorts 'department' values and .head as specified
inp5.lower()
if inp5 == 'high to low' or inp5 == 'high low' or inp5 == 'h l' or inp5 == 'descending':
inp6 = int(input('How many values would you like to assess?\n(Give an integer value)\n'))
spec = spec.sort_values(['Salary'], ascending=False)
spec = spec.head(inp6)
spec.reset_index(drop=True, inplace=True)
spec.index += 1
spec_avg = spec['Salary'].mean()
spec_min = spec['Salary'].min()
spec_max = spec['Salary'].max()
print('\nFor',yn,'in the',inp3,'department:\n(Pay sorted',inp5,'and top',inp6,'values)\n')
print('The minimum pay was','$%0.2f'%spec_min)
print('The maximum pay was','$%0.2f'%spec_max)
print('The average pay was','$%0.2f'%spec_avg,'\n')
print(spec)
if inp6 > 499:
whisker_func(spec, yn, inp3)
spec_quick_500(spec)
scatter(spec)
print(spec.head(20))
if inp6 > 249 and inp6 < 500:
whisker_func(spec, yn, inp3)
spec_quick_250(spec)
print(spec.head(20))
if inp6 > 99 and inp6 < 250:
whisker_func(spec, yn, inp3)
spec_quick_100(spec)
print(spec.head(20))
if inp6 > 49 and inp6 < 100:
whisker_func(spec, yn, inp3)
spec_quick_50(spec)
print(spec.head(20))
if inp6 > 24 and inp6 < 50:
whisker_func(spec, yn, inp3)
spec_quick_25(spec)
print(spec)
if inp6 > 9 and inp6 < 25:
whisker_func(spec, yn, inp3)
spec_quick_10(spec)
print(spec)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if inp5 == 'low to high' or inp5 == 'low high' or inp5 == 'l h' or inp5 == 'ascending':
spec = spec.sort_values(['Salary'], ascending=True)
inp6 = int(input('How many values would you like to assess?\n(Give an integer value)\n'))
spec = spec.head(inp6)
spec.reset_index(drop=True, inplace=True)
spec.index += 1
spec_avg = spec['Salary'].mean()
spec_min = spec['Salary'].min()
spec_max = spec['Salary'].max()
print('\nFor',yn,'in the',inp3,'department:\n(Pay sorted',inp5,'and top',inp6,'values)\n')
print('The minimum pay was','$%0.2f'%spec_min)
print('The maximum pay was','$%0.2f'%spec_max)
print('The average pay was','$%0.2f'%spec_avg,'\n')
print(spec)
if inp6 > 499:
whisker_func(spec, yn, inp3)
spec_bot_500(spec)
print(spec.head(20))
if inp6 > 249 and inp6 < 500:
whisker_func(spec, yn, inp3)
spec_bot_250(spec)
print(spec.head(20))
if inp6 > 99 and inp6 < 250:
whisker_func(spec, yn, inp3)
spec_bot_100(spec)
print(spec.head(20))
if inp6 > 49 and inp6 < 100:
whisker_func(spec, yn, inp3)
spec_bot_50(spec)
print(spec.head(20))
if inp6 > 24 and inp6 < 50:
whisker_func(spec, yn, inp3)
spec_bot_25(spec)
print(spec)
if inp6 > 9 and inp6 < 25:
whisker_func(spec, yn, inp3)
spec_bot_10(spec)
print(spec)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if inp4 == 'no' or inp4 == 'n' or inp4 == 'nah':
spec = spec
print('Okay!')
#-----------------------------------------------------------------------------------------------------------------------------------------
#The following code loops through code pertaining to a positive departmental summary response
if inp2 == 'various' or inp2 =='multiple':
dep_lis = list()
titles = year['Title'].value_counts()
print('Different titles with value counts:\n',titles.head(20),'\n')
inp3 = input('Which titles?\n-----Up to 3-----\n(Separate by comma)\n')
inp3 = inp3.upper()
inp3 = inp3.split(",")
inp3list = list()
for i in inp3:
i = str(i)
i = i.lstrip()
inp3list.append(i)
print(inp3list)
length = len(inp3list)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
x = 0
while x < length:
if x == 0:
key = inp3list[x]
spec = year.loc[key == year['Title']]
x = x + 1
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if x == 1:
key = inp3list[x]
spec2 = year.loc[key == year['Title']]
x = x + 1
clean = pd.concat([spec,spec2])
spec = clean
continue
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if x == 2:
key = inp3list[x]
spec3 = year.loc[key == year['Title']]
x = x + 1
clean = pd.concat([clean, spec3])
spec = clean
continue
#--------------------------------------------------------------------------------------------------------------------------------------------
#The following code allows the user to specify value sort and .head()
print('\nWould you like to further analyze',inp3list,'for',yn,'?\n')
inp4 = input('Yes or no?\n')
inp4.lower()
if inp4 == 'yes' or inp4 == 'y' or inp4 == 'yeah':
if spec['Title'].count() < 1:
print('\nSorry.\nThere were no results.\nGoodbye')
else:
inp5 = input('Sort high to low(descending) or low to high values(ascending)?\n') #This block sorts 'department' values and .head as specified
inp5.lower()
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if inp5 == 'high to low' or inp5 == 'high low' or inp5 == 'h l' or inp5 == 'descending':
inp6 = int(input('How many values would you like to assess?\n(Give an integer value)\n'))
spec = spec.sort_values(['Salary'], ascending=False)
spec = spec.head(inp6)
spec.reset_index(drop=True, inplace=True)
spec.index += 1
spec_avg = spec['Salary'].mean()
spec_min = spec['Salary'].min()
spec_max = spec['Salary'].max()
print('\nFor',yn,'with the',inp3,'title:\n(Pay sorted',inp5,'and top',inp6,'values)\n')
print('The minimum pay was','$%0.2f'%spec_min)
print('The maximum pay was','$%0.2f'%spec_max)
print('The average pay was','$%0.2f'%spec_avg,'\n')
print(spec)
if inp6 > 499:
whisker_func(spec, yn, inp3list)
spec_quick_500(spec)
print(spec.head(20))
if inp6 > 249 and inp6 < 500:
whisker_func(spec, yn, inp3list)
spec_quick_250(spec)
print(spec.head(20))
if inp6 > 99 and inp6 < 250:
whisker_func(spec, yn, inp3list)
spec_quick_100(spec)
print(spec.head(20))
if inp6 > 49 and inp6 < 100:
whisker_func(spec, yn, inp3list)
spec_quick_50(spec)
print(spec.head(20))
if inp6 > 24 and inp6 < 50:
whisker_func(spec, yn, inp3list)
spec_quick_25(spec)
print(spec)
if inp6 > 9 and inp6 < 25:
whisker_func(spec, yn, inp3list)
spec_quick_10(spec)
print(spec)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if inp5 == 'low to high' or inp5 == 'low high' or inp5 == 'l h' or inp5 == 'ascending':
spec = spec.sort_values(['Salary'], ascending=True)
inp6 = int(input('How many values would you like to assess?\n(Give an integer value)\n'))
spec = spec.head(inp6)
spec.reset_index(drop=True, inplace=True)
spec.index += 1
spec_avg = spec['Salary'].mean()
spec_min = spec['Salary'].min()
spec_max = spec['Salary'].max()
print('\nFor',yn,'in the',inp3,'department:\n(Pay sorted',inp5,'and top',inp6,'values)\n')
print('The minimum pay was','$%0.2f'%spec_min)
print('The maximum pay was','$%0.2f'%spec_max)
print('The average pay was','$%0.2f'%spec_avg,'\n')
if inp6 > 499:
whisker_func(spec, yn, inp3list)
spec_bot_500(spec)
print(spec.head(20))
if inp6 > 249 and inp6 < 500:
whisker_func(spec, yn, inp3list)
spec_bot_250(spec)
print(spec.head(20))
if inp6 > 99 and inp6 < 250:
whisker_func(spec, yn, inp3list)
spec_bot_100(spec)
print(spec.head(20))
if inp6 > 49 and inp6 < 100:
whisker_func(spec, yn, inp3list)
spec_bot_50(spec)
print(spec.head(20))
if inp6 > 24 and inp6 < 50:
whisker_func(spec, yn, inp3list)
spec_bot_25(spec)
print(spec)
if inp6 > 9 and inp6 < 25:
whisker_func(spec, yn, inp3list)
spec_bot_10(spec)
print(spec)
# - - - - - - - - - - - - - - - - - - - - - - - - - - -
if inp4 == 'no' or inp4 == 'n' or inp4 == 'nah':
print('Okay! Bye!')
In [17]:
pd.set_option('display.width', 300)
def yearplot(data):
inp = input('Which field/s are you interested in?\n(Department, Title)\n')
inp = inp.lower()
if inp == 'dept' or inp == 'department' or inp == 'departments':
year_plt_dept(year)
if inp == 'title' or inp == 'job title' or inp == 'job':
year_plt_title(year)
yearplot(year)
In [ ]: