continue
#export the pVals2 as a csv
for rep in pVals2:
pVals2[rep].to_csv(os.path.join(savedir, str(rep) + 'sigPs.csv' ))
#make some violin plots of the significant features
from feature_swarms import swarms
cmap2 = sns.color_palette("Blues", len(allConcs))
sns.set_style('whitegrid')
for rep in pVals2:
for feat in range(0,10):
#swarms (str(rep), sig_feats[rep][feat][0], featMatZ2[featMatZ2['date']==rep], savedir, '.tif', cmap)
swarms('all', sig_feats[rep][feat][0], featMatZ2 ,savedir, '.tif', cmap2)
# =============================================================================
# Things to do:
# 1. Train classifier to distinguish between Atypical and typical drugs
# 2. check DMSO controls on all dates and plot to compare
# 3. Make a list of the drugs to repeat - DONE
# =============================================================================
#%% Compare features across reps
for date in allDates:
plt.figure()
del ps, temp3, temp4
del temp, temp2, conc
#export the pVals2 as a csv
for rep in pVals2:
pVals2[rep].to_csv(os.path.join(directoryA[:-7], rep + 'sigPs.csv' ))
#make some violin plots of the significant features
import feature_swarms as swarm
cmap = sns.color_palette("tab20", len(uniqueDrugs))
sns.set_style('whitegrid')
for rep in featuresA2:
for feat in range(0,10):
swarm.swarms (rep, sig_feats[rep][feat][0], featuresA2[rep], directoryA, '.tif', cmap)
#make a list of any of the features that are significantly different in all experiments
stats_feats = []
for rep in sig_feats:
stats_feats += list(list(zip(*sig_feats[rep]))[0])
stats_feats = np.unique(stats_feats)
#%% reduce the feature set to the significant ones - for Clozapine10
#make a list combined from all reps
cloz10Feats = []
for rep in pVals2:
cloz10 = pVals2[rep][pVals2[rep]['drug'] == 'Clozapine'][pVals2[rep]['concentration']==10.0]
cloz10Feats += list(cloz10.columns[np.where(cloz10.notnull())[1]])
del cloz10
sig_feats[rep].append(
(bh_p[rep].columns[feat], np.sum(top_feats[rep][:, feat])))
#sort by most to least
sig_feats[rep].sort(key=lambda tup: tup[1])
sig_feats[rep].reverse()
#make some violin plots of the significant features
import feature_swarms as swarm
cmap = sns.color_palette("tab20", len(uniqueDrugs))
sns.set_style('whitegrid')
for rep in featuresL2:
for feat in range(0, 10):
swarm.swarms(rep, sig_feats[rep][feat][0], featuresL2[rep], directoryL,
'.tif', cmap)
#so looks like can pull out differences between DMSO and chloropromazine and clozapine. Data is messier probably
#because only one repeat
#%% classifier v1
#use only features that are significant to train the classifier
#convert the list of tuples into a list of features
bh_list = [i[0] for i in sig_feats[rep]]
#only 120 features
featMatAllL3 = featMatAllL[bh_list]
featMatAllL3['drug'] = drug_allL
featMatAllL3['concentration'] = conc_allL
featMatAllL3['date'] = date_allL
feat_scores = pd.DataFrame(data = np.array(temp), columns = mr_Feats2)
del temp
#now find out which features are in the top and bottom 10%, and then only take forward \
#those that are in the top/bottom 10% in 50% of the CVs
bottom = list(feat_scores.columns[np.sum(feat_scores<=15)>=5]) #bottom 10%
top = list(feat_scores.columns[np.sum(feat_scores>=135)>=5]) #top 10%
#combine
combi = top + bottom
#22 features
#plot these as swarms:
import feature_swarms as swarm
for item in combi:
swarm.swarms('all', item, featMatAll, directoryA, '.tif', cmap1 )
plt.close()
#make a dataframe of this final featurespace
final_feat = pd.concat([mrFeatMatFinal[combi], mrFeatMatFinal.iloc[:,-3:]], axis=1)
final_feat['class'] = conds2['drug']
#make a clustergram
#1. make lut for drug colors
#make a colormap and lookup table
cmap1 = sns.color_palette("tab20", np.unique(final_feat['class']).shape[0])
lut = dict(zip(np.unique(final_feat['class']), cmap1))
#add in row colors to the dataframe
row_colors = final_feat['class'].map(lut)#map onto the feature Matrix
del ps, temp3, temp4
del temp, temp2, conc
#export the pVals2 as a csv
for rep in pVals2:
pVals2[rep].to_csv(os.path.join(directoryA[:-7], rep + 'sigPs.csv'))
#make some violin plots of the significant features
import feature_swarms as swarm
cmap = sns.color_palette("Blues", len(uniqueDrugs))
sns.set_style('whitegrid')
for rep in featuresA2:
for feat in range(0, 10):
swarm.swarms('all', sig_feats[rep][feat][0], featMatAll, directoryA,
'.tif', cmap)
#make a list of any of the features that are significantly different in all experiments
stats_feats = []
for rep in sig_feats:
stats_feats += list(list(zip(*sig_feats[rep]))[0])
stats_feats = np.unique(stats_feats)
#%% reduce the feature set to the significant ones - for Clozapine10
#make a list combined from all reps
cloz10Feats = []
for rep in pVals2:
cloz10 = pVals2[rep][pVals2[rep]['drug'] == 'Clozapine'][
pVals2[rep]['concentration'] == 10.0]
cloz10Feats += list(cloz10.columns[np.where(cloz10.notnull())[1]])