import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline

import seaborn as sns
sns.set_palette("deep", desat=.6)
sns.set_context(rc={"figure.figsize": (11, 6)})

import matplotlib as mpl
mpl.rcParams['font.sans-serif'].insert(0, 'Arial')
mpl.rcParams['font.sans-serif'].insert(0, 'Liberation Sans')
mpl.rcParams['font.family'] = 'sans-serif'

df = pd.read_csv('./ndata.csv')

df['conference'].unique().size

conf_year = df.groupby(['conference', 'year'])
len(conf_year)

df['gender'].describe()

df['gender'].value_counts()

# take only male and female, ignore the rest
df = df[(df.gender == 'male') | (df.gender == 'female')]
df['gender'].value_counts()

gender_plot= df['gender'].value_counts().plot(kind = 'bar', title = 'Overall gender frequency in the collected data')
plt.savefig('gender_plot.png',  bbox_inches='tight')

per_year = pd.crosstab(df['year'], df['gender'])
per_year

per_ear_plot = per_year.plot(kind='bar', stacked=True, title="Gender per year")
plt.savefig(r'gender_per_year.png', bbox_inches='tight')

per_year_perc = per_year.div(per_year.sum(axis = 1), axis = 0)

per_ear_plot = per_year_perc.plot(kind='bar', stacked=True, title="Gender frequency per year")
plt.savefig(r'gender_freq_per_year.png', bbox_inches='tight')

conf_year = df.groupby(['conference', 'year'])
conf_year['gender'].value_counts(normalize = True).to_dict()

conf_data = df[(df.conference == 'Golden Gate Ruby Conference') ]
conf_data_year = pd.crosstab(conf_data['year'], conf_data['gender'])
conf_data_year.plot(kind = 'bar', stacked  = True, title = 'Golden Gate Ruby Conference')

conf_data = df[(df.conference == 'strangeloop.com') ]
conf_data_year = pd.crosstab(conf_data['year'], conf_data['gender'])
conf_data_year.plot(kind = 'bar', stacked  = True, title = 'strangeloop.com')

conf_data = df[(df.conference == 'PyCon US') ]
conf_data_year = pd.crosstab(conf_data['year'], conf_data['gender'])
conf_data_year.plot(kind = 'bar', stacked  = True, title = 'PyCon US')

conf_data = df[(df.conference == 'Cascadia Ruby') ]
conf_data_year = pd.crosstab(conf_data['year'], conf_data['gender'])
conf_data_year.plot(kind = 'bar', stacked  = True, title = 'Cascadia Ruby')

conf_data = df[(df.conference == 'Farmhouse Conf') ]
conf_data_year = pd.crosstab(conf_data['year'], conf_data['gender'])
conf_data_year.plot(kind = 'bar', stacked  = True, title = 'Farmhouse Conf')