02.basic_statistic

In [1]:

import pandas as pd

df = pd.read_csv("./data/gapminder.tsv", sep="\t")

In [2]:

print(df.head(n=10))

       country continent  year  lifeExp       pop   gdpPercap
0  Afghanistan      Asia  1952   28.801   8425333  779.445314
1  Afghanistan      Asia  1957   30.332   9240934  820.853030
2  Afghanistan      Asia  1962   31.997  10267083  853.100710
3  Afghanistan      Asia  1967   34.020  11537966  836.197138
4  Afghanistan      Asia  1972   36.088  13079460  739.981106
5  Afghanistan      Asia  1977   38.438  14880372  786.113360
6  Afghanistan      Asia  1982   39.854  12881816  978.011439
7  Afghanistan      Asia  1987   40.822  13867957  852.395945
8  Afghanistan      Asia  1992   41.674  16317921  649.341395
9  Afghanistan      Asia  1997   41.763  22227415  635.341351

groupby¶

In [3]:

print(df.groupby("year")["lifeExp"].mean())
print("\n======================================\n")
print(df.groupby("continent")["country"].nunique())
print("\n======================================\n")

year
1952    49.057620
1957    51.507401
1962    53.609249
1967    55.678290
1972    57.647386
1977    59.570157
1982    61.533197
1987    63.212613
1992    64.160338
1997    65.014676
2002    65.694923
2007    67.007423
Name: lifeExp, dtype: float64

======================================

continent
Africa      52
Americas    25
Asia        33
Europe      30
Oceania      2
Name: country, dtype: int64

======================================

In [4]:

df.groupby(["year", "continent"])["lifeExp"].mean()

Out[4]:

year  continent
1952  Africa       39.135500
      Americas     53.279840
      Asia         46.314394
      Europe       64.408500
      Oceania      69.255000
1957  Africa       41.266346
      Americas     55.960280
      Asia         49.318544
      Europe       66.703067
      Oceania      70.295000
1962  Africa       43.319442
      Americas     58.398760
      Asia         51.563223
      Europe       68.539233
      Oceania      71.085000
1967  Africa       45.334538
      Americas     60.410920
      Asia         54.663640
      Europe       69.737600
      Oceania      71.310000
1972  Africa       47.450942
      Americas     62.394920
      Asia         57.319269
      Europe       70.775033
      Oceania      71.910000
1977  Africa       49.580423
      Americas     64.391560
      Asia         59.610556
      Europe       71.937767
      Oceania      72.855000
1982  Africa       51.592865
      Americas     66.228840
      Asia         62.617939
      Europe       72.806400
      Oceania      74.290000
1987  Africa       53.344788
      Americas     68.090720
      Asia         64.851182
      Europe       73.642167
      Oceania      75.320000
1992  Africa       53.629577
      Americas     69.568360
      Asia         66.537212
      Europe       74.440100
      Oceania      76.945000
1997  Africa       53.598269
      Americas     71.150480
      Asia         68.020515
      Europe       75.505167
      Oceania      78.190000
2002  Africa       53.325231
      Americas     72.422040
      Asia         69.233879
      Europe       76.700600
      Oceania      79.740000
2007  Africa       54.806038
      Americas     73.608120
      Asia         70.728485
      Europe       77.648600
      Oceania      80.719500
Name: lifeExp, dtype: float64

graph¶

In [5]:

%matplotlib inline
import matplotlib.pyplot as plt

plt.rcParams["figure.figsize"] = (12, 9)
plt.rcParams['axes.unicode_minus'] = False

In [6]:

lifeExp = df.groupby("year")["lifeExp"].mean()
lifeExp.plot()
plt.show()

In [7]:

from IPython.core.display import display, HTML

display(HTML("<style> .container{width:100% !important;}</style>"))