def run():
datadict = load_data()
model = iONMF(rank=5, max_iter=100, alpha=0.0)
# Fit all training data
model.fit(datadict)
# Make predictions about class on all training data
# using only expression data ...
testdict = dict()
testdict["Pos_diff_expr"] = datadict["Pos_diff_expr"]
testdict["Neg_diff_expr"] = datadict["Neg_diff_expr"]
rdict = model.predict(testdict)
# ... and calculate training error
true_y = np.zeros((len(datadict["Class_0"]), 1))
true_y[np.where(datadict["Class_0"])] = 0
true_y[np.where(datadict["Class_1"])] = 1
true_y[np.where(datadict["Class_2"])] = 2
predictions = np.array([
np.argmax(
[rdict["Class_0"][i], rdict["Class_1"][i], rdict["Class_2"][i]])
for i in xrange(len(true_y))
])
acc = np.sum(predictions == true_y.ravel()) / float(len(true_y))
print "Training accuracy: ", acc
# Plot matrices
plt.figure(figsize=(12, 12))
for ki, ky in enumerate(testdict.keys()):
plt.subplot(len(testdict), 2, 2 * ki + 1)
plt.title(ky)
plt.imshow(datadict[ky])
plt.subplot(len(testdict), 2, 2 * ki + 2)
plt.title(ky + " (approx.)")
plt.imshow(model.coef_.dot(model.basis_[ky]))
plt.show()
def run():
datadict = load_data()
model = iONMF(rank=5, max_iter=100, alpha=0.0)
# Fit all training data
model.fit(datadict)
# Make predictions about class on all training data
# using only expression data ...
testdict = dict()
testdict["Pos_diff_expr"] = datadict["Pos_diff_expr"]
testdict["Neg_diff_expr"] = datadict["Neg_diff_expr"]
rdict = model.predict(testdict)
# ... and calculate training error
true_y = np.zeros((len(datadict["Class_0"]), 1))
true_y[np.where(datadict["Class_0"])] = 0
true_y[np.where(datadict["Class_1"])] = 1
true_y[np.where(datadict["Class_2"])] = 2
predictions = np.array([np.argmax([rdict["Class_0"][i], rdict["Class_1"][i],
rdict["Class_2"][i]])
for i in xrange(len(true_y))])
acc = np.sum(predictions == true_y.ravel()) / float(len(true_y))
print "Training accuracy: ", acc
# Plot matrices
plt.figure(figsize=(12, 12))
for ki, ky in enumerate(testdict.keys()):
plt.subplot(len(testdict), 2, 2*ki+1)
plt.title(ky)
plt.imshow(datadict[ky])
plt.subplot(len(testdict), 2, 2*ki+2)
plt.title(ky + " (approx.)")
plt.imshow(model.coef_.dot(model.basis_[ky]))
plt.show()
def run():
# Select example protein folder from the dataset
protein = sys.argv[1]
# Load training data and column labels
training_data = load_data("../datasets/clip/%s/5000/training_sample_0"
% protein,
go=False, kmer=False)
training_labels = load_labels("../datasets/clip/%s/5000/training_sample_0"
% protein, go=False, kmer=False)
model = iONMF(rank=5, max_iter=100, alpha=10.0)
# Fit all training data
model.fit(training_data)
# Make predictions about class on all training data
# delete class from dictionary
test_data = load_data("../datasets/clip/%s/5000/test_sample_0" % protein,
go=False, kmer=False)
true_y = test_data["Y"].copy()
del test_data["Y"]
results = model.predict(test_data)
# Evaluate prediction on holdout test set
predictions = results["Y"]
auc = roc_auc_score(true_y, predictions)
print "Test AUC: ", auc
# Draw low-dimensional components for Region types (H_RG)
# and RNA structure (H_RNA)
# with mean values in coefficient matrix W for positive (+) and negative (-)
# positions
f, axes = plt.subplots(model.rank, 3, sharex='col',
figsize=(15, 8))
H_RNA = model.basis_["X_RNA"]
H_RG = model.basis_["X_RG"]
labelset = sorted(set(training_labels["X_RG"]))
positives = training_data["Y"].nonzero()[0]
negatives = (training_data["Y"] == 0).nonzero()[0]
for k in xrange(model.rank):
# Values in the coefficient (W) matrix
w_positives = model.coef_[positives, :][:, k].mean()
w_negatives = model.coef_[negatives, :][:, k].mean()
e_positives = model.coef_[positives, :][:, k].std() / np.sqrt(len(positives))
e_negatives = model.coef_[negatives, :][:, k].std() / np.sqrt(len(negatives))
axes[k, 2].bar([0], [w_negatives], yerr =[(0,), (e_positives, )],
color="blue", align="center")
axes[k, 2].bar([1], [w_positives], yerr =[(0,), (e_negatives, )],
color="green", align="center")
# Plot RNA structure
axes[k, 1].plot(H_RNA[k, :].ravel(),)
# Plot region types
for label in labelset:
indices = np.where(map(lambda e: e == label, training_labels["X_RG"]))[0]
axes[k, 0].plot(H_RG[k, indices].ravel(), label=label)
axes[k, 0].set_ylabel("Module %d" % k)
j = model.rank - 1
axes[0, 0].legend(bbox_to_anchor=(0., 1.04, 1., .102), loc=3,
ncol=3, mode="expand", borderaxespad=0.)
axes[0, 1].set_title("Double-stranded RNA")
axes[0, 2].set_title("Mean values in the coefficient matrix (W)")
axes[j, 0].set_xticks(np.linspace(0, H_RNA.shape[1], 5))
axes[j, 0].set_xticklabels([-50, -25, 0, 25, 50])
axes[j, 0].set_xlabel("Position relative to cross-link site")
axes[j, 1].set_xticks(np.linspace(0, H_RNA.shape[1], 5))
axes[j, 1].set_xticklabels([-50, -25, 0, 25, 50])
axes[j, 1].set_xlabel("Position relative to cross-link site")
axes[j, 2].set_xticks([0, 1])
axes[j, 2].set_xticklabels(["-", "+"])
plt.show()
