In [1]:
%matplotlib inline
import numpy as np
import scipy.stats as stats
import matplotlib.pyplot as plt
import pandas as pd
In [2]:
births_url = "https://goo.gl/pFAL23"
births = pd.read_table(births_url)
In [4]:
births.head(n=10)
Out[4]:
In [6]:
births.visits.isnull().sum()
Out[6]:
In [7]:
births.isnull().sum()
Out[7]:
In [10]:
births.smoke.unique()
Out[10]:
In [11]:
nfullterm = births.premature == "full term"
nfullterm.sum()
Out[11]:
In [12]:
npremie = births.premature == "premie"
npremie.sum()
Out[12]:
In [13]:
births[npremie]
Out[13]:
In [20]:
#babyGirls = births.query('sexBaby == "female"')
#babyGirls = births[births.sexBaby == "female"]
isgirl = births.sexBaby == "female"
births[isgirl].shape
Out[20]:
In [16]:
babyGirls.shape
Out[16]:
In [21]:
isboy = births.sexBaby == "male"
births[isboy].shape
Out[21]:
In [22]:
ispremie = births.premature == "premie"
In [23]:
premieGirls = births[isgirl & ispremie]
In [24]:
premieGirls
Out[24]:
In [26]:
isbig = births.weight > 9
isbig.sum()
Out[26]:
In [32]:
boys = births.sexBaby != "female"
In [30]:
births[nofAge]
In [39]:
births.groupby(["smoke","sexBaby"])
Out[39]:
In [42]:
g = births.groupby('smoke').describe()
g
Out[42]:
In [43]:
## Matplotlib
In [46]:
plt.scatter(births.mAge, births.fAge)
plt.xlabel("Mother's Age")
plt.ylabel("Father's Age")
plt.title("My useful title")
Out[46]:
In [47]:
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 0.8, 0.8])
In [49]:
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 0.8, 0.8])
axes.scatter(births.mAge, births.fAge)
axes.set_xlabel("Age of Mother")
axes.set_ylabel("Age of Father")
pass
In [57]:
fig = plt.figure(figsize=(6,6))
axes = fig.add_axes([0.1, 0.1, 0.5, 0.5])
axes.scatter(births.mAge, births.fAge)
axes.set_xlabel("Age of Mother")
axes.set_ylabel("Age of Father")
rightax = fig.add_axes([0.7, 0.1, 0.25, 0.5])
rightax.hist(births.mAge, normed=True,orientation="horizontal" )
above = fig.add_axes([0.1, 0.7, 0.5, 0.25])
above.hist(births.mAge, normed=True)
above.set_xlim(10,50)
pass
In [ ]: