}
}
train = ct.get_feature_all(feature_dict)
label = ct.get_numeric_label({'cooperative': 1, 'additive': 0})
rf_param_grid = {
'n_estimators': [1000], #[500,750,1000],
'max_depth': [10], #[5,10,15],
"min_samples_leaf": [10], #[5,10,15],
"min_samples_split": [10] #[5,10,15]
}
best_models = {
"all":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df(feature_dict)).run_all()
}
pl.plot_model_metrics(best_models,
cvfold=10,
score_type="auc",
varyline=True,
title="Average ROC Curves for Runx1-Ets1")
# # This is usually made based on the best model
rf = ensemble.RandomForestClassifier(n_estimators=1000,
max_depth=10,
min_samples_leaf=10,
min_samples_split=10)
rf.fit(train, label)
model_name = "dist_ori_12merimads.sav"
rf_param_grid = {
'n_estimators': [500, 100, 1500],
'max_depth': [5, 10, 15],
"min_samples_leaf": [10, 15, 20],
"min_samples_split": [10, 15, 20]
}
# TODO: choose per orientation
best_models = {
"dist,ori":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=cooptr.get_training_df({
"distance": {
"type": "numerical"
},
"orientation": {
"positive_cores": ["GGAA", "GGAT"],
"one_hot": True
}
}),
topn=10).run_all(),
"dist,shape_inout":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=cooptr.get_training_df({
"distance": {
"type": "numerical"
},
"shape_in": {
"seqin": 4,
"smode": "strength",
df['label'] = df['label'].replace('independent', 'additive')
ct = CoopTrain(df)
pd.set_option("display.max_columns", None)
rf_param_grid = {
'n_estimators': [500], #[500,750,1000],
'max_depth': [5], #[5,10,15],
"min_samples_leaf": [5], #[5,10,15],
"min_samples_split": [5] #[5,10,15]
}
best_models = {
"strength":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df(
{"affinity": {
"colnames": ("ets_score", "runx_score")
}})).run_all(),
"distance":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df(
{"distance": {
"type": "numerical"
}})).run_all(),
"orientation":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df({
"orientation": {
"relative": False,
pd.set_option("display.max_columns", None)
rf_param_grid = {
'n_estimators': [1000], #[500,750,1000],
'max_depth': [10], #[5,10,15],
"min_samples_leaf": [5], #[5,10,15],
"min_samples_split": [5] #[5,10,15]
}
best_models = {
"Weaker site strength":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df(
{"affinity": {
"colnames": ["site_str_score"]
}},
label_map={
'cooperative': 1,
'independent': 0
})).run_all(),
"Stronger site strength":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df(
{"affinity": {
"colnames": ["site_wk_score"]
}},
label_map={
'cooperative': 1,
'independent': 0
})).run_all(),
"min_samples_leaf": [10], #[5,10,15],
"min_samples_split": [20], #[5,10,15]
}
best_models = {
"distance,orientation":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df(
{
"distance": {
"type": "numerical"
},
"orientation": {
"relative": rel_ori,
"one_hot": one_hot_ori,
"pos_cols": {
"%s_pos" % s1: "%s_ori" % s1,
"%s_pos" % s2: "%s_ori" % s2
}
},
},
label_map={
'cooperative': 1,
'independent': 0
})).run_all(),
"distance,orientation,sequence":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df(
{
"distance": {
rf_param_grid = {
'n_estimators': [500], #[500,750,1000],
'max_depth': [10], #[5,10,15],
"min_samples_leaf": [10], #[5,10,15],
"min_samples_split": [20], #[5,10,15]
}
best_models = {
"distance,orientation":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df({
"distance": {
"type": "numerical"
},
"orientation": {
"relative": False,
"pos_cols": {
"ets_pos": "ets_ori",
"runx_pos": "runx_ori"
}
}
})).run_all(),
"distance,orientation,sequence":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=ct.get_training_df({
"distance": {
"type": "numerical"
},
"orientation": {
"relative": False,
# using custom imads model
imads8_paths = ["input/site_models/imads_models/Ets1_w8_GGAA.model", "input/site_models/imads_models/Ets1_w8_GGAT.model"]
imads8_cores = ["GGAA", "GGAT"]
imads8_models = [iMADSModel(path, core, 8, [1, 2, 3]) for path, core in zip(imads8_paths, imads8_cores)]
imads8 = iMADS(imads8_models, 0.19) # 0.2128
imads12_paths = ["input/site_models/imads_models/Ets1_w12_GGAA.model", "input/site_models/imads_models/Ets1_w12_GGAT.model"]
imads12_cores = ["GGAA", "GGAT"]
imads12_models = [iMADSModel(path, core, 12, [1, 2, 3]) for path, core in zip(imads12_paths, imads12_cores)]
imads12 = iMADS(imads12_models, 0.19) # 0.2128
best_models = {
"distance":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=cooptr.get_training_df({
"distance":{"type":"numerical"}
})
).run_all(),
"orientation":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=cooptr.get_training_df({
"orientation": {"positive_cores":["GGAA","GGAT"], "one_hot":True}
})
).run_all(),
"strength":
BestModel(clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=cooptr.get_training_df({
"affinity": {"imads": imads12}
})
'n_estimators': [500, 1000, 1500],
'max_depth': [5, 10, 15],
"min_samples_leaf": [5, 10, 15],
"min_samples_split": [5, 10, 15]
}
orientations = ["HH", "TT", "HT/TH"]
for ori in orientations:
curdf = df[df["orientation"] == ori]
curct = CoopTrain(curdf, corelen=4, positive_cores=["GGAA", "GGAT"])
best_models = {
"distance":
BestModel(
clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=curct.get_training_df(
{"distance": {
"type": "numerical"
}}),
).run_all(score_type=score_type),
"shape":
BestModel(
clf="sklearn.ensemble.RandomForestClassifier",
param_grid=rf_param_grid,
train_data=curct.get_training_df({
"shape_in": {
"seqin": 4,
"smode": "positional",
"direction": "inout"
}, # maximum seqin is 4
"shape_out": {
"seqin": -4,