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]:
# For each subquestion, plot the data
subquestions = ["D39[SQ001]","D39[SQ002]","D39[SQ003]","D39[SQ004]"]
subquestions_value = [u"2011",
u"2012",
u"2013",
u"2014"]
In [5]:
%%capture output
# Save the output as a variable that can be saved to a file
space = {}
for k,i in enumerate(subquestions):
space[k] = data[i].value_counts(dropna=False)
print ""
print "Data:",subquestions_value[k]
print space
print ""
print "Data %:"
print data[i].value_counts(normalize=True, dropna=False) * 100
print ""
print "Data: statistics:"
print data[i].describe()
In [6]:
# Save+show the output to a text file
%save Q039-Bilancio.py str(output)
shutil.move("Q039-Bilancio.py", "text/Q039-Bilancio.txt")
In [7]:
# Swap nan for a more understandable word
space2 = {}
for i in space:
old_dict = space[i].to_dict()
new_dict = {}
for k in old_dict:
if isinstance(k, numpy.float64) and np.isnan(k):
new_dict["Nessuna risposta"] = old_dict[k]
elif type(k) is float and np.isnan(k):
new_dict["Nessuna risposta"] = old_dict[k]
else:
new_dict[k] = old_dict[k]
gradou = pd.Series(new_dict)
space2[i] = gradou.order()
In [8]:
for k,i in enumerate(space2):
# Plot the data 01
plt.figure(figsize=(8,6))
plt.xlabel(subquestions_value[k], fontsize=16)
plt.ylabel('Lab', fontsize=16)
plt.title(u"Qual è stato il bilancio annuale del laboratorio? €", fontsize=18, y=1.02)
my_colors = seaborn.color_palette("husl", len(space)) # Set color palette
space2[i].plot(kind="bar",color=my_colors)
plt.savefig(u"svg/Q039-"+subquestions_value[k]+"01.svg")
plt.savefig(u"png/Q039-"+subquestions_value[k]+"01.png")
plt.savefig(u"pdf/Q039-"+subquestions_value[k]+"01.pdf")
In [9]:
# Plot the data 02
for k,i in enumerate(space2):
# Reorder value_counts by index natural order
space1 = space2[i].sort_index()
plt.figure(figsize=(8,6))
plt.title(u"Qual è stato il bilancio annuale del laboratorio? €", fontsize=18, y=1.02)
plt.xlabel(subquestions_value[k], 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/Q039-"+subquestions_value[k]+"02.svg")
plt.savefig(u"png/Q039-"+subquestions_value[k]+"02.png")
plt.savefig(u"pdf/Q039-"+subquestions_value[k]+"02.pdf")
In [10]:
for k,i in enumerate(space2):
# Check histogram
plt.figure(figsize=(8,6))
plt.title(u"Qual è stato il bilancio annuale del laboratorio? € "+subquestions_value[k], fontsize=18, y=1.02)
plt.xlabel(subquestions_value[k], fontsize=16)
plt.ylabel('Lab', fontsize=16)
space2[i].hist(bins=60)
plt.savefig(u"svg/Q039-"+subquestions_value[k]+"03.svg")
plt.savefig(u"png/Q039-"+subquestions_value[k]+"03.png")
plt.savefig(u"pdf/Q039-"+subquestions_value[k]+"03.pdf")
In [10]: