def compare_column_across_conditions(column, df):
df = df.copy() # Don't modify what was passed in
lim_pirna_common.add_conditions_and_sample_types(df)
comparison_df = pd.DataFrame(index=SAMPLE_NAMES.values(), columns=['WT mean', 'pin/pin mean', 'p-value'])
for (sample_type, sample_df) in df.groupby("sample_type"):
condition_gb = sample_df.groupby("condition")[column]
wt = condition_gb.get_group('WT')
mut = condition_gb.get_group('pin/pin')
(_, p) = stats.ttest_ind(wt, mut)
sample_stats = comparison_df.ix[sample_type]
sample_stats['WT mean'] = wt.mean()
sample_stats['pin/pin mean'] = mut.mean()
sample_stats['p-value'] = p
comparison_df.to_csv("%s_comparison.csv" % column.replace(' ', '_'))
def plot_sequence_lengths(description, sequence_lengths_df, min_length, max_length):
graph_dir = "%s_read_length_graphs" % description
sacgf_utils.mk_path(graph_dir)
total_reads = sequence_lengths_df.sum(axis=1)
reads_percent = sequence_lengths_df.divide(total_reads / 100.0, axis=0)
max_percent = reads_percent.max().max()
y_limit = np.floor(1 + max_percent / 5) * 5 # use multiples of 5
add_conditions_and_sample_types(reads_percent)
for (sample_type, sample_df) in reads_percent.groupby(SAMPLE_TYPE):
for (color_scheme, colors) in colour_sets.iteritems():
for plot_mean in [False, True]:
mean_description = "_mean" if plot_mean else ""
graph_image = "read_lengths_%s%s_%s_boxplot" % (color_scheme, mean_description, sample_type)
graph_image = os.path.join(graph_dir, graph_image)
plot_greyscale_boxplot(graph_image, description, sample_type, sample_df, colors, y_limit, min_length, max_length, plot_mean)
def save_df_with_condition_and_samples(filename, df):
df = df.copy() # Don't modify what was passed in
lim_pirna_common.add_conditions_and_sample_types(df)
df.to_csv(filename)
