Q036 - Quante sono le persone che utilizzano il laboratorio?

In [1]:

    

# -*- coding: UTF-8 -*-

# Render our plots inline
%matplotlib inline 

import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import seaborn
import shutil

pd.set_option('display.mpl_style', 'default') # Make the graphs a bit prettier, overridden by seaborn
pd.set_option('display.max_columns', None) # Display all the columns
plt.rcParams['font.family'] = 'sans-serif' # Sans Serif fonts for all the graphs

# Reference for color palettes: http://web.stanford.edu/~mwaskom/software/seaborn/tutorial/color_palettes.html

# Change the font
matplotlib.rcParams.update({'font.family': 'Source Sans Pro'})


    

In [2]:

    

# Load csv file first
data = pd.read_csv("data/lab-survey.csv", encoding="utf-8")


    

In [3]:

    

# Check data
#data[0:4] # Equals to data.head()


    

In [4]:

    

%%capture output

# Save the output as a variable that can be saved to a file
# Get the distribution of ages
space = data["D36"].value_counts(dropna=False)
print "Data:"
print space
print ""
print "Data %:"
print data["D36"].value_counts(normalize=True,dropna=False) * 100
print ""
print "Data: statistics:"
print data["D36"].describe()


    

In [5]:

    

# Save+show the output to a text file
%save Q036-NumeroUtenti.py str(output)
shutil.move("Q036-NumeroUtenti.py", "text/Q036-NumeroUtenti.txt")


    

    




The following commands were written to file `Q036-NumeroUtenti.py`:
Data:
NaN     19
 30     11
 20     10
 10      8
 15      3
 5       3
 50      2
 12      2
 6       2
 3       2
 25      1
 150     1
 60      1
 130     1
 100     1
 2       1
 35      1
 40      1
dtype: int64

Data %:
NaN     27.142857
 30     15.714286
 20     14.285714
 10     11.428571
 15      4.285714
 5       4.285714
 50      2.857143
 12      2.857143
 6       2.857143
 3       2.857143
 25      1.428571
 150     1.428571
 60      1.428571
 130     1.428571
 100     1.428571
 2       1.428571
 35      1.428571
 40      1.428571
dtype: float64

Data: statistics:
count     51.000000
mean      26.549020
std       28.752262
min        2.000000
25%       10.000000
50%       20.000000
75%       30.000000
max      150.000000
Name: D36, dtype: float64

In [6]:

    

# Swap nan for a more understandable word
old_dict = space.to_dict()
new_dict = {}
for i in old_dict:
    if isinstance(i, numpy.float64) and np.isnan(i):
        new_dict["Nessuna risposta"] = old_dict[i]
    elif type(i) is float and np.isnan(i):
        new_dict["Nessuna risposta"] = old_dict[i]
    else:
        new_dict[i] = old_dict[i]

spaceu = pd.Series(new_dict)
space = spaceu.order()


    

In [7]:

    

# Plot the data 01
plt.figure(figsize=(8,6))
plt.xlabel(u'Numero utenti', fontsize=16)
plt.ylabel('Lab', fontsize=16)
plt.title(u"Quante sono le persone che utilizzano il laboratorio?", fontsize=18, y=1.02)
my_colors = seaborn.color_palette("husl", len(space)) # Set color palette
space.plot(kind="bar",color=my_colors)
plt.savefig(u"svg/Q036-NumeroUtenti01.svg")
plt.savefig(u"png/Q036-NumeroUtenti01.png")
plt.savefig(u"pdf/Q036-NumeroUtenti01.pdf")


    

In [8]:

    

# Plot the data 02

# Reorder value_counts by index (age) natural order
space1 = space.sort_index()

plt.figure(figsize=(8,6))
plt.title(u'Quante sono le persone che utilizzano il laboratorio?', fontsize=18, y=1.02)
plt.xlabel(u'Numero utenti', fontsize=16)
plt.ylabel('Lab', fontsize=16)

# Plot the data
my_colors = seaborn.color_palette("husl", len(space1)) # Set color palette
space1.plot(kind='bar',color=my_colors)
plt.savefig(u"svg/Q036-NumeroUtenti02.svg")
plt.savefig(u"png/Q036-NumeroUtenti02.png")
plt.savefig(u"pdf/Q036-NumeroUtenti02.pdf")


    

In [9]:

    

# Check histogram
plt.figure(figsize=(8,6))
plt.title(u'Quante sono le persone che utilizzano il laboratorio?', fontsize=18, y=1.02)
plt.xlabel(u'Numero utenti', fontsize=16)
plt.ylabel('Lab', fontsize=16)
data["D36"].hist(bins=60)
plt.savefig(u"svg/Q036-NumeroUtenti03.svg")
plt.savefig(u"png/Q036-NumeroUtenti03.png")
plt.savefig(u"pdf/Q036-NumeroUtenti03.pdf")


    

In [9]: