Información de Fisher nivel nodo: Sitio Metztitlan

Dra. Melanie Kolb
M. en F. C. Gustavo Magallanes-Guijón
Dr. Oliver López-Corona

In [2]:

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import sys, os
import datetime
from matplotlib.pylab import rcParams
%matplotlib inline
import warnings
import seaborn as sns
import functools

In [3]:

!ls *.csv > lista.txt

In [4]:

lista = pd.read_csv('lista.txt', header = None)
list_of_rows = [j for j in lista.values]
# Print list of lists i.e. rows
len(list_of_rows)

Out[4]:

In [5]:

filesnames = os.listdir()
filesnames = [f for f in filesnames if (f.endswith(".csv"))]

In [6]:

dfs = list()
string = "_df"
for filename in filesnames:
    #print(filename)
    #nueva = string.join(filename)
    df = pd.read_csv(filename)
    dfs.append(df)

In [9]:

merged = pd.merge(dfs[0], dfs[1])
#for i in range(len(dfs)):
for i in range(len(dfs)):
    merged = pd.merge(merged, dfs[i])

In [ ]:

In [10]:

merged

Out[10]:

	473.0	20.3333	0.1646	0.0003	301.0	0.5155	7.85	0.0179	0.9534	10462.0	...	40.0	10.0	0.17657143	0.0003432	0.4332	0.016157143	0.7268	187.5	2012-12-05	193.466

0 rows × 39 columns

In [61]:

merged = pd.merge(dfs[0], dfs[1])

In [97]:

merged = pd.merge(merged, dfs[39]) #13, 38
merged

Out[97]:

	2012-12-05	473.0	20.3333	0.1646	0.0003	301.0	0.5155	7.85	0.0179	0.9534	...	0.0864	36.0	40.0	10.0	0.17657143	0.0003432	0.4332	0.016157143	0.7268	193.466
0	2014-08-12	246.0	23.8	0.097000	0.000160	1723.0	0.445000	8.0	0.039000	1.158000	...	0.072000	50.00	77.5	20.000000	0.030000	0.000110	1.256000	0.004400	1.943000	160.00
1	2015-06-16	323.0	25.8	0.097999	0.000155	10.0	0.096172	7.8	0.002875	0.755858	...	0.053206	42.00	25.0	104.500000	0.018667	0.000148	0.037583	0.004900	0.618837	199.61
2	2015-09-13	774.0	22.1	0.096771	0.000069	5475.0	0.104798	7.7	0.030934	0.753085	...	0.035550	54.00	55.0	189.000000	0.022000	0.000096	1.166088	0.034700	1.853759	82.51
3	2016-03-05	426.0	22.3	0.032482	0.000374	31.0	0.042899	8.4	0.016863	0.975848	...	0.171312	64.00	36.0	129.333330	0.024000	0.000206	0.049949	0.005800	0.922659	204.34
4	2016-09-18	794.0	23.6	0.112780	0.000100	52.0	0.163656	7.9	0.045480	1.275159	...	0.036990	30.00	30.0	69.666664	0.063000	0.000104	0.824911	0.086092	1.368339	152.64
5	2018-02-11	530.0	20.7	0.151770	0.000096	74.0	0.198454	8.1	0.026406	0.853729	...	0.062647	34.00	30.0	30.000000	0.110000	0.000065	0.487336	0.008300	0.863120	222.72
6	2019-02-15	265.0	23.5	0.026774	0.000044	20.0	0.071418	8.5	0.002813	0.627657	...	0.036650	27.74	20.0	41.000000	0.053000	0.000044	0.008934	0.007337	0.930861	202.77

7 rows × 39 columns

In [98]:

from sklearn import preprocessing

df_num = merged.select_dtypes(include=[np.number])

x = df_num.values #returns a numpy array
min_max_scaler = preprocessing.MinMaxScaler()
x_scaled = min_max_scaler.fit_transform(x)
df_num = pd.DataFrame(x_scaled)
df_num

Out[98]:

	0	1	2	3	4	5	6	7	8	9	...	28	29	30	31	32	33	34	35	36	37
0	0.000000	0.607843	0.561826	0.351515	0.313449	1.000000	0.375	0.848126	0.819060	1.000000	...	0.268485	0.613900	1.000000	0.000000	0.124088	0.408624	1.000000	0.000000	1.000000	0.552671
1	0.140511	1.000000	0.569818	0.336364	0.000000	0.132487	0.125	0.001453	0.197993	0.098008	...	0.130051	0.393271	0.086957	0.500000	0.000000	0.642710	0.022973	0.006121	0.000000	0.835176
2	0.963504	0.274510	0.559994	0.075758	1.000000	0.153939	0.000	0.659081	0.193711	0.770211	...	0.000000	0.724214	0.608696	1.000000	0.036496	0.322382	0.927901	0.370907	0.932606	0.000000
3	0.328467	0.313725	0.045665	1.000000	0.003843	0.000000	0.875	0.329294	0.537745	0.000000	...	1.000000	1.000000	0.278261	0.646943	0.058394	1.000000	0.032889	0.017138	0.229445	0.868911
4	1.000000	0.568627	0.688070	0.169697	0.007685	0.300315	0.250	1.000000	1.000000	0.409868	...	0.010607	0.062328	0.173913	0.293886	0.485401	0.371663	0.654317	1.000000	0.566019	0.500178
5	0.518248	0.000000	1.000000	0.157576	0.011711	0.386856	0.500	0.552957	0.349145	0.001348	...	0.199592	0.172642	0.173913	0.059172	1.000000	0.131417	0.383622	0.047740	0.184481	1.000000
6	0.034672	0.549020	0.000000	0.000000	0.001830	0.070925	1.000	0.000000	0.000000	0.804291	...	0.008102	0.000000	0.000000	0.124260	0.375912	0.000000	0.000000	0.035954	0.235639	0.857713

7 rows × 38 columns

In [99]:

result = pd.concat([merged.select_dtypes(np.object), df_num], axis=1)
result

Out[99]:

	2012-12-05	0	1	2	3	4	5	6	7	8	...	28	29	30	31	32	33	34	35	36	37
0	2014-08-12	0.000000	0.607843	0.561826	0.351515	0.313449	1.000000	0.375	0.848126	0.819060	...	0.268485	0.613900	1.000000	0.000000	0.124088	0.408624	1.000000	0.000000	1.000000	0.552671
1	2015-06-16	0.140511	1.000000	0.569818	0.336364	0.000000	0.132487	0.125	0.001453	0.197993	...	0.130051	0.393271	0.086957	0.500000	0.000000	0.642710	0.022973	0.006121	0.000000	0.835176
2	2015-09-13	0.963504	0.274510	0.559994	0.075758	1.000000	0.153939	0.000	0.659081	0.193711	...	0.000000	0.724214	0.608696	1.000000	0.036496	0.322382	0.927901	0.370907	0.932606	0.000000
3	2016-03-05	0.328467	0.313725	0.045665	1.000000	0.003843	0.000000	0.875	0.329294	0.537745	...	1.000000	1.000000	0.278261	0.646943	0.058394	1.000000	0.032889	0.017138	0.229445	0.868911
4	2016-09-18	1.000000	0.568627	0.688070	0.169697	0.007685	0.300315	0.250	1.000000	1.000000	...	0.010607	0.062328	0.173913	0.293886	0.485401	0.371663	0.654317	1.000000	0.566019	0.500178
5	2018-02-11	0.518248	0.000000	1.000000	0.157576	0.011711	0.386856	0.500	0.552957	0.349145	...	0.199592	0.172642	0.173913	0.059172	1.000000	0.131417	0.383622	0.047740	0.184481	1.000000
6	2019-02-15	0.034672	0.549020	0.000000	0.000000	0.001830	0.070925	1.000	0.000000	0.000000	...	0.008102	0.000000	0.000000	0.124260	0.375912	0.000000	0.000000	0.035954	0.235639	0.857713

7 rows × 39 columns

In [100]:

result.to_csv("master.csv",index=False, header=False)

In [101]:

os.chdir("fisher-nodo/")

In [102]:

fs = !ls *.png

import IPython.display as dp

# create list of image objects
images = []
for ea in fs:
    images.append(dp.Image(filename=ea, format='png'))

# display all images
for ea in images:
    dp.display_png(ea)