#!/usr/bin/env python
# coding: utf-8

# Datas collected in https://www.nsf.gov/statistics/nsf13327/content.cfm?pub_id=4266&id=2

# In[1]:


import pandas as pd
import numpy as np
import seaborn as sns
get_ipython().run_line_magic('pylab', 'inline')


sns.set(style="darkgrid")
df = pd.read_csv('datasbio.csv')
df.set_index(["Academic year ending"])
df.head(6)


# In[2]:


df["Percent Male Bachelor's"]=df["Male Bachelor's"]/df["All recipients Bachelor's"]*100
df["Percent Female Bachelor's"]=df["Female Bachelor's"]/df["All recipients Bachelor's"]*100
df["Percent Male Master's"]=df["Male Master's"]/df["All recipients Master's"]*100
df["Percent Female Master's"]=df["Female Master's"]/df["All recipients Master's"]*100
df["Percent Male Doctoratea"]=df["Male Doctoratea"]/df["All recipients Doctoratea"]*100
df["Percent Female Doctoratea"]=df["Female Doctoratea"]/df["All recipients Doctoratea"]*100
df["total"]=df["All recipients Bachelor's"]+df["All recipients Master's"]+df["All recipients Doctoratea"]
df["Male total"]=df["Male Bachelor's"]+df["Male Master's"]+df["Male Doctoratea"]
df["Female total"]=df["Female Bachelor's"]+df["Female Master's"]+df["Female Doctoratea"]
df["Percent Male total"]=df["Male total"]*100/df["total"]
df["Percent Female total"]=df["Female total"]*100/df["total"]
#differences between years
d=[0]
for i in range(1,len(df["All recipients Bachelor's"])):
    d.append(df["All recipients Bachelor's"][i]-df["All recipients Bachelor's"][i-1])
df["Difference All recipients Bachelor's"]=d

d=[0]
for i in range(1,len(df["Male Bachelor's"])):
    d.append(df["Male Bachelor's"][i]-df["Male Bachelor's"][i-1])
df["Difference Male Bachelor's"]=d

d=[0]
for i in range(1,len(df["Female Bachelor's"])):
    d.append(df["Female Bachelor's"][i]-df["Female Bachelor's"][i-1])
df["Difference Female Bachelor's"]=d

d=[0]
for i in range(1,len(df["All recipients Master's"])):
    d.append(df["All recipients Master's"][i]-df["All recipients Master's"][i-1])
df["Difference All recipients Master's"]=d

d=[0]
for i in range(1,len(df["Male Master's"])):
    d.append(df["Male Master's"][i]-df["Male Master's"][i-1])
df["Difference Male Master's"]=d

d=[0]
for i in range(1,len(df["Female Master's"])):
    d.append(df["Female Master's"][i]-df["Female Master's"][i-1])
df["Difference Female Master's"]=d


d=[0]
for i in range(1,len(df["All recipients Doctoratea"])):
    d.append(df["All recipients Doctoratea"][i]-df["All recipients Doctoratea"][i-1])
df["Difference All recipients Doctoratea"]=d

d=[0]
for i in range(1,len(df["Male Doctoratea"])):
    d.append(df["Male Doctoratea"][i]-df["Male Doctoratea"][i-1])
df["Difference Male Doctoratea"]=d

d=[0]
for i in range(1,len(df["Female Doctoratea"])):
    d.append(df["Female Doctoratea"][i]-df["Female Doctoratea"][i-1])
df["Difference Female Doctoratea"]=d

d=[0]
for i in range(1,len(df["total"])):
    d.append(df["total"][i]-df["total"][i-1])
df["Difference total"]=d

d=[0]
for i in range(1,len(df["Male total"])):
    d.append(df["Male total"][i]-df["Male total"][i-1])
df["Difference Male total"]=d

d=[0]
for i in range(1,len(df["Female total"])):
    d.append(df["Female total"][i]-df["Female total"][i-1])
df["Difference Female total"]=d


df=df.fillna(0)
df.set_index(["Academic year ending"])
df.head()


# In[3]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only percent total
df_p_total=df[["Academic year ending","Percent Female total","Percent Male total"]]
df_p_total.set_index("Academic year ending").plot()


# In[4]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only total
df_total=df[["Academic year ending","Female total","Male total"]]
df_total.set_index("Academic year ending").plot()


# In[5]:


df.head()


# In[6]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only Percent female
df_p_female=df[["Academic year ending","Percent Female Bachelor's","Percent Female Master's","Percent Female Doctoratea","Percent Female total"]]
df_p_female.set_index("Academic year ending").plot()


# In[7]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only female
df_female=df[["Academic year ending","Female Bachelor's","Female Master's","Female Doctoratea","Female total"]]
df_female.set_index("Academic year ending").plot()


# In[8]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only male
df_male=df[["Academic year ending","Male Bachelor's","Male Master's","Male Doctoratea","Male total"]]
df_male.set_index("Academic year ending").plot()


# In[9]:


df.head()


# In[10]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only male
df_male=df[["Academic year ending","Difference Male Bachelor's","Difference Male Master's","Difference Male Doctoratea","Difference Male total"]]
df_male.set_index("Academic year ending").plot()


# In[11]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only male
df_male=df[["Academic year ending","Difference Female Bachelor's","Difference Female Master's","Difference Female Doctoratea","Difference Female total"]]
df_male.set_index("Academic year ending").plot()


# In[12]:


pylab.rcParams['figure.figsize'] = (20, 18)
#df only male
df_male=df[["Academic year ending","Difference Male Bachelor's","Difference Female Bachelor's"]]
df_male.set_index("Academic year ending").plot()