Browse Source

update draft notebook

dev
Francois Vieille 6 months ago
parent
commit
005e808d39
5 changed files with 496 additions and 148 deletions
  1. +211
    -0
      notebooks/advanced_clustering.py
  2. +1
    -4
      notebooks/classical_clustering.py
  3. +11
    -30
      notebooks/test_clustering.ipynb
  4. +250
    -107
      notebooks/test_model_class.ipynb
  5. +23
    -7
      notebooks/test_mysql.ipynb

+ 211
- 0
notebooks/advanced_clustering.py View File

@@ -0,0 +1,211 @@
#%% [markdown]
# # Clustering classique

#%% [markdown]
# ## import classique
import os

#%%
%load_ext autoreload
%autoreload 2
os.chdir('/home/jovyan/work')

#%% [markdown]
# ## Import iss

#%%
from iss.tools import Config
from iss.tools import Tools
from iss.models import SimpleConvAutoEncoder
from iss.clustering import ClassicalClustering
from iss.clustering import AdvancedClustering
from dotenv import find_dotenv, load_dotenv
import numpy as np

#%% [markdown]
# ## Chargement de la config

#%%
load_dotenv(find_dotenv())
cfg = Config(project_dir = os.getenv("PROJECT_DIR"), mode = os.getenv("MODE"))

#%% [markdown]
# ## Chargement du modèle

#%%
## charger le modèle

model_type = 'simple_conv'
cfg.get('models')[model_type]['model_name'] = 'model_colab'
model = SimpleConvAutoEncoder(cfg.get('models')[model_type])

#%% [markdown]
## Chargement des images

#%%
filenames = Tools.list_directory_filenames('data/processed/models/autoencoder/train/k/')
generator_imgs = Tools.generator_np_picture_from_filenames(filenames, target_size = (27, 48), batch = 496, nb_batch = 10, scale = 1/255)


#%%
pictures_id, pictures_preds = Tools.encoded_pictures_from_generator(generator_imgs, model)

#%%
intermediate_output = pictures_preds.reshape((pictures_preds.shape[0], 3*6*16))


#%%
clustering = AdvancedClustering(cfg.get('clustering')['advanced'], pictures_id, intermediate_output)


#%%
clustering.compute_pca()


#%%
clustering.compute_kmeans()

#%%
clustering.compute_kmeans_centers()

#%%
len(clustering.kmeans_centers)

#%%
clustering.dbscan_args = {'eps': 50, 'min_samples':1}
clustering.compute_dbscan()

#%%
clustering.compute_dbscan_labels()

#%%
len(clustering.final_labels)

#%%
np.unique(clustering.final_labels, return_counts = True)

#%%[markdown]
# # Graphiques

#%%
def select_cluster(clustering, id_cluster):
return [os.path.join('data/processed/models/autoencoder/train/k/', res[0] + '.jpg') for res in clustering.get_zip_results() if res[2] == id_cluster]


#%%
for cl in np.unique(clustering.kmeans_labels):
print("Cluster %s" % (cl))
res_tmp = select_cluster(clustering, cl)
if len(res_tmp) >= 0:
print(len(res_tmp))
image_array = [Tools.read_np_picture(f, target_size = (54, 96)) for f in res_tmp[:100]]
img = Tools.display_mosaic(image_array, nrow = 10)
fig = plt.figure(1, figsize=(12, 7))
plt.imshow(img, aspect = 'auto')
plt.show()

#%% [markdown]
# ## faut essayer de faire des paquets

#%%
from sklearn.manifold import TSNE

output_tnse = TSNE(n_components=2).fit_transform(clustering.pca_reduction)


#%%
plt.scatter(
output_tnse[:,0],
output_tnse[:,1],
c = clustering.kmeans_labels
)
plt.show()

#%%
from sklearn.cluster import KMeans

tmp_km = KMeans(n_clusters = 15)
tmp_res = tmp_km.fit(output_tnse)

#%%
tmp_res.labels_

#%%
plt.scatter(
output_tnse[:,0],
output_tnse[:,1],
c = tmp_res.labels_
)
plt.show()


#%%
clustering.final_labels = tmp_res.labels_



#%%
from scipy.cluster.hierarchy import dendrogram
from sklearn.cluster import AgglomerativeClustering

#%%
def plot_dendrogram(model, **kwargs):

# Children of hierarchical clustering
children = model.children_

# Distances between each pair of children
# Since we don't have this information, we can use a uniform one for plotting
distance = np.arange(children.shape[0])

# The number of observations contained in each cluster level
no_of_observations = np.arange(2, children.shape[0]+2)

# Create linkage matrix and then plot the dendrogram
linkage_matrix = np.column_stack([children, distance, no_of_observations]).astype(float)

# Plot the corresponding dendrogram
dendrogram(linkage_matrix, **kwargs)

#%%
cah_fit = AgglomerativeClustering(n_clusters=10)

#%%
cah_fit = cah_fit.fit(clustering.kmeans_centers)

#%%
fig = plt.figure(1, figsize=(12, 7))
plot_dendrogram(cah_fit, labels = cah_fit.labels_)

#%%
cah_fit.labels_

#%%
tmp = Tools.read_np_picture('data/processed/models/autoencoder/train/k/20171109-192001.jpg',target_size = (27, 48), scale = 1/255)
tmp = tmp.reshape((1,27,48,3))
np.sum(model.get_encoded_prediction(tmp))

#%%
filenames = Tools.list_directory_filenames('data/processed/models/autoencoder/train/k/')
generator_imgs = Tools.generator_np_picture_from_filenames(filenames, target_size = (27, 48), batch = 10, nb_batch = 3, scale = 1/255)

predictions_list = []
predictions_id = []
for imgs in generator_imgs:
predictions_id.append(imgs[0])
predictions_list.append(model.get_encoded_prediction(imgs[1]))

#%%
np.concatenate(tuple(predictions_list), axis = 0)[0,:,:,:]

#%%
predictions_list[0][0,:,:,:]

#%%
print(pictures_preds[1,:,:,:])


#%%
pictures_preds.shape

#%%

+ 1
- 4
notebooks/classical_clustering.py View File

@@ -18,6 +18,7 @@ from iss.tools import Config
from iss.tools import Tools
from iss.models import SimpleConvAutoEncoder
from iss.clustering import ClassicalClustering
from iss.clustering import AdvancedClustering
from dotenv import find_dotenv, load_dotenv
import numpy as np

@@ -149,7 +150,3 @@ plt.scatter(clustering.pca_reduction[:, 0], clustering.pca_reduction[:, 1], c =

#%%
plt.scatter(clustering.pca_reduction[np.array(col) == 1, 0], clustering.pca_reduction[np.array(col) == 1, 1])



#%%

+ 11
- 30
notebooks/test_clustering.ipynb View File

@@ -147,48 +147,29 @@
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"i_debut:0\n",
"i_fin:496\n",
"i_debut:496\n",
"i_fin:992\n"
]
}
],
"outputs": [],
"source": [
"pictures_preds = Tools.encoded_pictures_from_generator(generator_imgs, model)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(992, 3, 6, 16)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
"ename": "AttributeError",
"evalue": "'tuple' object has no attribute 'reshape'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-13-e3d22d0becf7>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mintermediate_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpictures_preds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m992\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m6\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m16\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m: 'tuple' object has no attribute 'reshape'"
]
}
],
"source": [
"pictures_preds.shape"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"intermediate_output = pictures_preds.reshape((992, 3*6*16))"
]
},


+ 250
- 107
notebooks/test_model_class.ipynb
File diff suppressed because it is too large
View File


+ 23
- 7
notebooks/test_mysql.ipynb View File

@@ -31,17 +31,21 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: MySQL-connector-python in /opt/conda/lib/python3.6/site-packages (8.0.15)\n",
"Requirement already satisfied: protobuf>=3.0.0 in /opt/conda/lib/python3.6/site-packages (from MySQL-connector-python) (3.6.1)\n",
"Collecting MySQL-connector-python\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/f7/59/c2220c52d747da492f2aed108cdf99b640b88cf89dbbe2ea13a8c04201aa/mysql_connector_python-8.0.18-cp36-cp36m-manylinux1_x86_64.whl (16.1MB)\n",
"\u001b[K 100% |████████████████████████████████| 16.1MB 4.1MB/s \n",
"\u001b[?25hRequirement already satisfied: protobuf>=3.0.0 in /opt/conda/lib/python3.6/site-packages (from MySQL-connector-python) (3.6.1)\n",
"Requirement already satisfied: six>=1.9 in /opt/conda/lib/python3.6/site-packages (from protobuf>=3.0.0->MySQL-connector-python) (1.12.0)\n",
"Requirement already satisfied: setuptools in /opt/conda/lib/python3.6/site-packages (from protobuf>=3.0.0->MySQL-connector-python) (40.8.0)\n"
"Requirement already satisfied: setuptools in /opt/conda/lib/python3.6/site-packages (from protobuf>=3.0.0->MySQL-connector-python) (40.8.0)\n",
"Installing collected packages: MySQL-connector-python\n",
"Successfully installed MySQL-connector-python-8.0.18\n"
]
}
],
@@ -51,7 +55,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
@@ -66,9 +70,21 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 6,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "TypeError",
"evalue": "__init__() missing 2 required positional arguments: 'project_dir' and 'mode'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-6-e6f50bbb757a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mcfg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mConfig\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m: __init__() missing 2 required positional arguments: 'project_dir' and 'mode'"
]
}
],
"source": [
"cfg = Config()"
]


Loading…
Cancel
Save