In [ ]:

    

%load_ext autoreload
%autoreload 2


    

In [ ]:

    

%run GLOBALS.py


    

In [ ]:

    

import matplotlib

matplotlib.use('TkAgg')
import matplotlib.pyplot as plt


    

In [ ]:

    

#import numpy as np
import os
import pandas as pd
import re
import seaborn as sns
#import matplotlib.pyplot as plt
%matplotlib inline


    

In [ ]:

    

import elviz_utils
import abundance_utils
import abundance_plot_utils


    

In [ ]:

    

data_reduced = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv")


    

In [ ]:

    

major_groups_dict = {'Phylum':['Bacteroidetes'], 
                    'Order':['Burkholderiales','Methylophilales',
                             'Methylococcales']}


    

In [ ]:

    

major_groups_df = abundance_plot_utils.aggregate_mixed_taxonomy(
    dataframe = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
    taxa_dict = major_groups_dict,
    main_dir = MAIN_DIR)

major_groups_df.head()


    

In [ ]:

    

m_dict = {'Genus':['Methylobacter', 'Methylovulum', 'Methylomonas', 'Methylomicrobium', 
              'Methyloglobulus', 'Methylococcus', 'Methylocaldum', 'Methylosarcina']}


    

In [ ]:

    

m_df = abundance_plot_utils.aggregate_mixed_taxonomy(
    dataframe = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
    taxa_dict = m_dict,
    main_dir = MAIN_DIR)

m_df.head()


    

In [ ]:

    

! ls ../results


    

In [ ]:

    

major_groups_filename = '../results/4_major_group_abundances.tsv'
major_groups_df.to_csv(major_groups_filename, sep='\t', index=False)


    

In [ ]:

    

m_filename = '../results/Methylococcales_and_Methylophilales_abundances.tsv'
m_df.to_csv(m_filename, sep='\t', index=False)