notebook.community

Edit and run 





In [1]:



    


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

from pandas import DataFrame, Series



    











In [2]:



    


fichero_pop_total = 'API_SP.POP.TOTL_DS2_es_csv_v2.csv'



    











In [ ]:



    






    











In [3]:



    


dfpoptotal = pd.read_csv(fichero_pop_total,sep=',',header=1,skiprows=2) #Lee un fichero csv



    











In [4]:



    


dfpoptotal.describe() # resumen estaditico de la data



    


















    
Out[4]:










  
    

      
      1960
      1961
      1962
      1963
      1964
      1965
      1966
      1967
      1968
      1969
      ...
      2008
      2009
      2010
      2011
      2012
      2013
      2014
      2015
      2016
      Unnamed: 61
    

  
  
    

      count
      2.600000e+02
      2.600000e+02
      2.600000e+02
      2.600000e+02
      2.600000e+02
      2.600000e+02
      2.600000e+02
      2.600000e+02
      2.600000e+02
      2.600000e+02
      ...
      2.630000e+02
      2.630000e+02
      2.630000e+02
      2.630000e+02
      2.620000e+02
      2.620000e+02
      2.620000e+02
      2.620000e+02
      0.0
      0.0
    

    

      mean
      1.184089e+08
      1.199950e+08
      1.221120e+08
      1.247393e+08
      1.273930e+08
      1.301080e+08
      1.329666e+08
      1.358183e+08
      1.387221e+08
      1.417697e+08
      ...
      2.708574e+08
      2.743544e+08
      2.778728e+08
      2.814299e+08
      2.860500e+08
      2.897585e+08
      2.934223e+08
      2.971317e+08
      NaN
      NaN
    

    

      std
      3.729446e+08
      3.773963e+08
      3.839358e+08
      3.924399e+08
      4.010045e+08
      4.097919e+08
      4.191425e+08
      4.284411e+08
      4.379496e+08
      4.479445e+08
      ...
      8.604460e+08
      8.709231e+08
      8.814713e+08
      8.921403e+08
      9.044301e+08
      9.154422e+08
      9.264383e+08
      9.375048e+08
      NaN
      NaN
    

    

      min
      4.279000e+03
      4.453000e+03
      4.566000e+03
      4.656000e+03
      4.748000e+03
      4.841000e+03
      4.936000e+03
      5.033000e+03
      5.161000e+03
      5.303000e+03
      ...
      9.788000e+03
      9.808000e+03
      9.827000e+03
      9.844000e+03
      9.860000e+03
      9.876000e+03
      9.893000e+03
      9.916000e+03
      NaN
      NaN
    

    

      25%
      5.179030e+05
      5.295098e+05
      5.418540e+05
      5.549710e+05
      5.681712e+05
      5.724870e+05
      5.782962e+05
      5.899358e+05
      6.290002e+05
      6.550080e+05
      ...
      1.363026e+06
      1.420972e+06
      1.436706e+06
      1.456044e+06
      1.409556e+06
      1.424658e+06
      1.443366e+06
      1.464251e+06
      NaN
      NaN
    

    

      50%
      3.669526e+06
      3.734208e+06
      3.811270e+06
      3.901628e+06
      4.020265e+06
      4.145164e+06
      4.235566e+06
      4.300506e+06
      4.367332e+06
      4.449020e+06
      ...
      9.132589e+06
      9.298515e+06
      9.490000e+06
      9.779391e+06
      9.976996e+06
      1.008062e+07
      1.013376e+07
      1.009667e+07
      NaN
      NaN
    

    

      75%
      2.532754e+07
      2.611541e+07
      2.690508e+07
      2.770050e+07
      2.847884e+07
      2.924675e+07
      2.999191e+07
      3.059503e+07
      3.120239e+07
      3.179527e+07
      ...
      5.016311e+07
      5.069532e+07
      5.125242e+07
      5.183768e+07
      5.249698e+07
      5.314012e+07
      5.390328e+07
      5.469198e+07
      NaN
      NaN
    

    

      max
      3.035056e+09
      3.076121e+09
      3.129064e+09
      3.193947e+09
      3.259355e+09
      3.326054e+09
      3.395866e+09
      3.465297e+09
      3.535512e+09
      3.609910e+09
      ...
      6.758303e+09
      6.840956e+09
      6.923684e+09
      7.006908e+09
      7.089452e+09
      7.176092e+09
      7.260780e+09
      7.346633e+09
      NaN
      NaN
    

  



8 rows × 58 columns



















In [5]:



    


dfpoptotal['2015'].describe() # describe la columna seleccionada



    


















    
Out[5]:








count    2.620000e+02
mean     2.971317e+08
std      9.375048e+08
min      9.916000e+03
25%      1.464251e+06
50%      1.009667e+07
75%      5.469198e+07
max      7.346633e+09
Name: 2015, dtype: float64

















In [6]:



    


dfpoptotal['2015'].value_counts(dropna=True)  # value_counts(), metodo que retorna la frecuencia para cada entrada única



    


















    
Out[6]:








1.744161e+09    2
1.000981e+09    2
7.726681e+07    1
5.957000e+06    1
1.138956e+07    1
2.851370e+07    1
7.748300e+05    1
4.605030e+07    1
7.304578e+06    1
4.900274e+06    1
4.224404e+06    1
4.490541e+06    1
2.515532e+07    1
2.129100e+04    1
3.129950e+07    1
1.440968e+08    1
6.680838e+07    1
5.535002e+06    1
3.474182e+06    1
1.311051e+09    1
3.178100e+04    1
1.849990e+05    1
9.150808e+07    1
1.609956e+08    1
1.850241e+07    1
6.183635e+09    1
6.795936e+07    1
5.495692e+07    1
3.308230e+05    1
8.380400e+06    1
               ..
5.876060e+05    1
1.044600e+05    1
5.061704e+07    1
5.389715e+07    1
5.557200e+04    1
3.880190e+05    1
1.371220e+09    1
3.903238e+07    1
1.580400e+05    1
3.110808e+07    1
4.422143e+06    1
4.240653e+08    1
1.659557e+09    1
8.141314e+07    1
2.096600e+07    1
7.305700e+06    1
1.068250e+05    1
9.181800e+04    1
3.799949e+07    1
1.128572e+07    1
6.802023e+06    1
5.373502e+06    1
6.053650e+08    1
1.889249e+08    1
2.797786e+07    1
1.560275e+07    1
7.268000e+04    1
4.524078e+09    1
3.805006e+07    1
1.000888e+09    1
Name: 2015, dtype: int64

Visualización de datos





In [7]:



    


# Histograma
dfpoptotal['2015'].plot(kind='hist', rot=70, logx=True, logy=True)

# show
plt.show()

Content source: JoseMambruDO/DataPortfolio

Similar notebooks:

notebook.community | gallery | about