def MitoseClassif(obj_norm,
y_name_3state="Type",classif_Mitose="MitoseOrNot",
num_str="0015"):
print "\n We first load the unnormalized data: \n"
if os.path.isfile("H2b_data.csv"):
print "The file existed so I loaded it."
H2b = Traj_data(file_name="H2b_data.csv",pkl_traj_file="./Pkl_file")
else:
H2b=Traj_data()
H2b.extracting(num_str,"both_channels_0015.hdf5",'primary')
## Extracting the hdf5 file for the primary channel (H2b)
H2b.Add_traj(normalize=False)## ,num_traj=10) ## (you can reduce the number of traj)
## Adding Alice's work on tracking to have trajectories
file_loc="0015_PCNA.xml"
H2b.label_finder(file_loc)
## Finding associated labels by minimizing distance by click and distance of cell
H2b.renaming_and_merge()
## renaming the labels to have G1=="1", S=="S", G2=="2" and M=="M"
#This procedure may take a long time.
H2b.data.to_csv('H2b_data.csv',index=False,header=True)
print "\n We train a classifier for mitosis or not: \n"
obj_unnorm=H2b
train_file="MitoseClassif.arff"
train_1=Reader()
train_1.arrf_read(train_file)
train_1.renaming_for_mitosis()
train_1.data["label"].value_counts()
kfold=3
if train_1.Var_missing[0] in train_1.data.columns:
train_1.missing_features_data()
values=[100 + i*10 for i in range(15)]
model_1=RandomForest_Autotunner(values)
model_1.tunning(train_1.data[train_1.names],train_1.data["label"],kfold,plot=True,fit_new_model=True)
plt.show()
model_1.cm_normalized = model_1.cm.astype('float') / model_1.cm.sum(axis=1)[:, np.newaxis]
plot_matrix(model_1.cm_normalized,title="Normalized confusion matrix",names=["M","O","S"])
plt.show()
## To reduce computation and none useless things, we remove instances that do not belong to trajectories.
obj_norm.data=obj_norm.data.ix[pd.notnull(obj_norm.data["traj"]),obj_norm.data.columns]
obj_unnorm.data=obj_unnorm.data.ix[pd.notnull(obj_unnorm.data["traj"]),obj_unnorm.data.columns]
obj_norm.update()
obj_unnorm.update()
## Predicting model 1
index_no_missing=obj_norm.data[obj_norm.names].dropna(axis=0, how='any').index
obj_norm.data.ix[index_no_missing,classif_Mitose]=model_1.predict(obj_unnorm.data.ix[index_no_missing,train_1.names])
## Carefull, we put the unnormalized data in the above prediction.
print "\n A bit of statistics on the overall predictions: \n"
print "Frequency of predicted values for the Mitosis or not classifier: \n"
print obj_norm.data[classif_Mitose].value_counts()
print "\n We were however not able to predict %d instances because of missing values" % (obj_norm.data.shape[0]-len(index_no_missing))
obj_norm.data
obj_norm.update()
### Giving priority to the first classif...
model_1.names_to_give=train_1.names
return(obj_norm,model_1)
