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_genus = pd.read_csv(MAIN_DIR + "results/reduced_data--genus_only.csv")
In [ ]:
abundance_utils.filter_by_abundance(data=data_reduced_genus,
abundance_column='fraction of reads', high=1, low=0.5).head()
In [ ]:
data_reduced_genus.head()
In [ ]:
# Change 'other' to 'other & unknown'
data_reduced_genus.ix[data_reduced_genus['Genus'] == 'other', 'Genus'] = r'other \& unknown'
data_reduced_genus.head()
In [ ]:
plot_path = PLOT_DIR + "/genus_only"
abundance_plot_utils.plot_heatmap_genus(dataframe=data_reduced_genus,
high=1, low = 0.5,
oxy='High', rep='all',
plot_dir=plot_path)
In [ ]:
# Loop through the ranges we want.
oxy_conditions = ['Low', 'High']
max_abundance = 1
range_pairs = [(0.01, max_abundance),
(0.05, max_abundance),
(0.1, max_abundance),
(0.5, max_abundance)]
for o in oxy_conditions:
for r in range_pairs:
#print "oxygen:", o
#print "range:", r
#print "range (low):", r[0]
abundance_plot_utils.plot_heatmap_genus(dataframe=data_reduced_genus,
low =r[0], high=r[1], oxy=o, rep='all',
plot_dir = PLOT_DIR + '/genus_only')
Import the data that was not reduced to Genus.
In [ ]:
data_reduced = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv")
In [ ]:
plot_1_spec_dict = {'Phylum':['Bacteroidetes'],
'Order':['Burkholderiales','Methylophilales',
'Methylococcales']}
In [ ]:
plot_1_data = abundance_plot_utils.aggregate_mixed_taxonomy(dataframe =
pd.read_csv(
MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
taxa_dict = plot_1_spec_dict,
main_dir = MAIN_DIR)
In [ ]:
plot_1_data.head()
In [ ]:
t_dicts = [
{'Phylum':['Bacteroidetes'],
'Order':['Burkholderiales', 'Methylophilales', 'Methylococcales']},
{'Genus':['Methylobacter', 'Methylovulum', 'Methylomonas', 'Methylomicrobium',
'Methyloglobulus', 'Methylococcus', 'Methylocaldum', 'Methylosarcina']},
{'Genus':['Methylotenera', 'Methylovorus', 'Methylophilus', 'Methylobacillus']}
]
In [ ]:
for t in t_dicts:
print(t)
print(abundance_plot_utils.taxa_dict_to_descriptive_string(t))
In [ ]:
print(MAIN_DIR)
print(PLOT_DIR)
In [ ]:
# plot without annotations
for t_dict in t_dicts:
abundance_plot_utils.heatmap_from_taxa_dict(
dataframe = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
taxa_dict = t_dict,
annotate=False,
main_dir = MAIN_DIR,
plot_dir= PLOT_DIR + '/mixed_taxonomy/')
In [ ]:
# plot with annotations
for t_dict in t_dicts:
abundance_plot_utils.heatmap_from_taxa_dict(dataframe =
pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
taxa_dict = t_dict,
facet = 'rep',
annotate = False,
main_dir = MAIN_DIR,
plot_dir = PLOT_DIR + '/mixed_taxonomy/')
In [ ]:
plot_name = os.path.join(PLOT_DIR, '170420_methanotroph_methylotroph_taxa' + '--portrait.pdf')
p = abundance_plot_utils.plot_dominant_methylotrophs(data_reduced_genus, plot_name)
In [ ]:
plot_name = os.path.join(PLOT_DIR, '170420_methanotroph_methylotroph_taxa' + '--landscape.pdf')
p = abundance_plot_utils.plot_dominant_methylotrophs(data_reduced_genus, plot_name, portrait=False)
In [ ]:
# make a png copy for defense 170420
plot_name = os.path.join(PLOT_DIR, '170420_methanotroph_methylotroph_taxa' + '--landscape.png')
p = abundance_plot_utils.plot_dominant_methylotrophs(data_reduced_genus, plot_name, portrait=False)
In [ ]:
pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv").head()
In [ ]:
abundance_plot_utils.plot_bars_for_taxa_dict(
dataframe = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
taxa_dict = plot_1_spec_dict,
order_list = ['Methylococcales', 'Methylophilales',
'Bacteroidetes', 'Burkholderiales', 'unknown \& other'],
summarize_other = True,
colors = ['#2c7fb8', '#feb24c', '#525252', '#969696', '#d9d9d9'],
main_dir = MAIN_DIR,
filename = os.path.join(PLOT_DIR + '/mixed_taxonomy/', '170413_4_main_groups.pdf'))
In [ ]:
p = abundance_plot_utils.plot_bars_for_taxa_dict(
dataframe = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
taxa_dict = plot_1_spec_dict,
order_list = ['Methylococcales', 'Methylophilales',
'Bacteroidetes', 'Burkholderiales', 'unknown \& other'],
summarize_other = True,
colors = ['#2c7fb8', '#feb24c', '#525252', '#969696', '#d9d9d9'],
main_dir = MAIN_DIR, portrait=False,
filename = os.path.join(PLOT_DIR + '/mixed_taxonomy/', '170413_4_main_groups--landscape.pdf'))
In [ ]:
p = abundance_plot_utils.plot_bars_for_taxa_dict(
dataframe = pd.read_csv(MAIN_DIR + "/results/reduced_data--all_taxonomy_remains.csv"),
taxa_dict = plot_1_spec_dict,
order_list = ['Methylococcales', 'Methylophilales',
'Bacteroidetes', 'Burkholderiales', 'unknown \& other'],
summarize_other = True,
colors = ['#2c7fb8', '#feb24c', '#525252', '#969696', '#d9d9d9'],
main_dir = MAIN_DIR, portrait=False,
filename = os.path.join(PLOT_DIR + '/mixed_taxonomy/', '170413_4_main_groups--landscape.png'))
In [ ]: