from __future__ import division
from numpy.random import randn
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
plt.rc('figure', figsize=(12, 5))
np.set_printoptions(precision=4)
%pwd

u'D:\\ipython'

import pandas as pd
names1880 = pd.read_csv('ch02/names/yob1880.txt', names=['name', 'sex', 'births'])
names1880

2000 rows × 3 columns

names1880.groupby('sex').births.sum()

sex
F     90993
M    110493
Name: births, dtype: int64

names

1690784 rows × 4 columns

total_births.tail()

total_births.plot(title='Total births by sex and year')

def get_top1000(group):return group.sort_index(by='births', ascending=False)[:1000]
grouped = names.groupby(['year', 'sex'])
top1000 = grouped.apply(get_top1000)

top1000

261877 rows × 4 columns

total_births = top1000.pivot_table('births', index='year', columns='name',aggfunc=sum)
total_births

131 rows × 6868 columns

subset = total_births[['John', 'Harry', 'Mary', 'Marilyn']]  # 分析这四个名字的趋势
subset.plot(subplots=True, figsize=(12, 10), grid=False,title="Number of births per year")

D:\python2713\lib\anaconda_install\lib\site-packages\matplotlib\transforms.py:661: RuntimeWarning: invalid value encountered in absoluteinside = ((abs(dx0 + dx1) + abs(dy0 + dy1)) == 0)

plt.figure()

<matplotlib.figure.Figure at 0xaa8dfd0>

table = top1000.pivot_table( index='year',columns='sex', aggfunc=sum)
table.plot(title='Sum of table1000.prop by year and sex',yticks=np.linspace(0, 1.2, 13), xticks=range(1880, 2020, 10))

subtable = table.reindex(columns=[1910, 1960, 2010], level='year')
subtable.head()
subtable.sum()

sex  year
F    1910     396416.01960    2022062.02010    1759010.0
M    1910     194198.01960    2132588.02010    1898382.0
dtype: float64

import matplotlib.pyplot as pltfig, axes = plt.subplots(2, 1, figsize=(10, 8))
letter_prop['M'].plot(kind='bar', rot=0, ax=axes[0], title='Male')
letter_prop['F'].plot(kind='bar', rot=0, ax=axes[1], title='Female',legend=False)

plt.subplots_adjust(hspace=0.25)

letter_prop = table / table.sum().astype(float)dny_ts = letter_prop.ix[['d', 'n', 'y'], 'M'].T
dny_ts.head()

D:\python2713\lib\anaconda_install\lib\site-packages\ipykernel_launcher.py:3: DeprecationWarning:
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexingSee the documentation here:
http://pandas.pydata.org/pandas-docs/stable/indexing.html#deprecate_ixThis is separate from the ipykernel package so we can avoid doing imports until

dny_ts.plot()

all_names = top1000.name.unique()
mask = np.array(['lesl' in x.lower() for x in all_names])
lesley_like = all_names[mask]
lesley_like

array(['Leslie', 'Lesley', 'Leslee', 'Lesli', 'Lesly'], dtype=object)

filtered = top1000[top1000.name.isin(lesley_like)]
filtered.groupby('name').births.sum()

name
Leslee      1082
Lesley     35022
Lesli        929
Leslie    370429
Lesly      10067
Name: births, dtype: int64

table = filtered.pivot_table('births', index='year',columns='sex', aggfunc='sum')
table = table.div(table.sum(1), axis=0)
table.tail()

table.plot(style={'M': 'k-', 'F': 'k--'})