def kernel(table, gamma=1, dbtype='mixed'):
if dbtype == 'mixed':
dist = gower.gower_matrix(table)
# kernel = np.power(table.shape[0], -gamma*dist)
kernel = np.exp(-gamma * dist)
# kernel = rbf_kernel(table, gamma)
# kernel = np.power(dist, np.shape(table)[0])
return kernel
def _define_noise_examples(self):
distances = gower.gower_matrix(self._attrs)
min_distances = [
self._cal_dNN(distances, indx)
for indx in range(self._labels.shape[0])
]
min_distances = pd.DataFrame(min_distances, columns=["distance"])
min_distances.sort_values("distance", ascending=False, inplace=True)
return list(min_distances[:self._num_noise].index)
def kernel_function(proto_critic, input):
gamma = 1
kernel = np.array([])
for idx in range(input.shape[0]):
dist = gower.gower_matrix(data_x=proto_critic,
data_y=np.reshape(input[idx, :],
(1, -1))).reshape((-1))
if idx == 0:
kernel = np.exp(-gamma * dist)
else:
kernel = np.vstack((kernel, np.exp(-gamma * dist)))
return kernel
def calc_gowers(df, continuous_columns):
"""Function to simplify calculating Gower's distance
Args:
df (pandas.DataFrame): dataframe of observations for which to calculate Gower's dstance \n
continuous_columns (list): list of integers identifying the indexes of columns that are continuous
Returns:
gow_dists (numpy.array): a numpy array of Gower's distances between observations
"""
cat_list = make_categorical_list(continuous_columns, len(df.columns) - 5)
data_np = df.iloc[:, 5:].to_numpy()
gow_dists = gower.gower_matrix(data_np, cat_features=cat_list)
return gow_dists
def calculate_distance(df):
# list of non boolean columns that require preprocessing
non_boolean_cols = [
'idade_empresa_anos', 'idade_maxima_socios', 'idade_media_socios',
'idade_minima_socios', 'qt_filiais', 'qt_socios',
'qt_socios_st_regular'
]
# normalizing the non boolean columns
df = min_max_col(df, non_boolean_cols)
# calculating the gower distance matrix
dissimilarity_matrix = gower.gower_matrix(df)
return dissimilarity_matrix
def N1(X, y, cat_features=[]):
"""
Calculate Fraction of Borderline Points (N1)
- X: ndarray features
- y: ndarray target
- cat_features: a boolean array that specifies categorical features
"""
if len(cat_features) == 0:
cat_features = np.zeros(X.shape[-1], dtype=bool)
# Calculate Gower distance matrix
distance_matrix = gower.gower_matrix(X, cat_features=cat_features)
# Generate a Minimum Spanning Tree
tree = MST(distance_matrix)
sub = tree[y[tree[:, 0]] != y[tree[:, 1]]]
vertices = np.unique(sub.flatten())
return len(vertices) / X.shape[0]
def cluster(df, random_state=None):
"""Use Gower distances and K Medioids to cluster the data from between 2 to 8 clusters.
Uses silhouette analysis to determine optimal number of clusters
Args:
df (pandas.DataFrame): The data in a pandas dataframe
random_state (int): Can be sued to fix the random state - ideal for testing
Returns:
(array): an array of the cluster assignments
(int): the number of clusters used
"""
# Compute the Gower distance matrix
# NOTE:large datasets will cause slow processing since array size is n2
matrix = gower.gower_matrix(df)
# Use silhouette analysis to determine the optimal number of clusters
# between 2 and 8 clusters
res = []
for k in range(2, 9):
#must have enough samples ie. k-1
if k < len(matrix) - 1:
k_medoids = KMedoids(n_clusters=k,
random_state=random_state).fit(matrix)
# Catch exceptions here and set the score to -1 (worst)
try:
silhouette_avg = silhouette_score(df, k_medoids.labels_)
res.append([k, silhouette_avg])
# If only one cluster causes an error so give worst score to this k
except ValueError:
res.append([k, -1])
# Best cluster has the value closest to 1 from the range -1 to 1
best_cluster = max(res, key=lambda x: x[1])
# Refit with the best number of clusters
k_medoids = KMedoids(n_clusters=best_cluster[0],
random_state=random_state).fit(matrix)
return k_medoids.labels_, best_cluster[0]
def test_answer():
Xd = pd.DataFrame({
'age': [21, 21, 19, 30, 21, 21, 19, 30, None],
'gender': ['M', 'M', 'N', 'M', 'F', 'F', 'F', 'F', None],
'civil_status': [
'MARRIED', 'SINGLE', 'SINGLE', 'SINGLE', 'MARRIED', 'SINGLE',
'WIDOW', 'DIVORCED', None
],
'salary': [
3000.0, 1200.0, 32000.0, 1800.0, 2900.0, 1100.0, 10000.0, 1500.0,
None
],
'has_children': [1, 0, 1, 1, 1, 0, 0, 1, None],
'available_credit':
[2200, 100, 22000, 1100, 2000, 100, 6000, 2200, None]
})
Yd = Xd.iloc[1:3, :]
X = np.asarray(Xd)
Y = np.asarray(Yd)
aaa = gower.gower_matrix(X)
assert aaa[0][1] == pytest.approx(0.3590238, 0.001)
cat_features = []
for col in df.columns:
if col not in num_features:
cat_features.append(col)
# scale standardization of numerical values
df_num = pd.DataFrame(StandardScaler().fit_transform(df[num_features]),columns=num_features)
df_cat = df.drop(columns=num_features)
df_std = df_cat.merge(df_num,left_index=True,right_index=True,how='left')
df_w_name = df_std
df_w_name.head()
df_std = df.set_index('DrinkName')
# generate similarity matrix
distance_matrix = gower.gower_matrix(df_std)
#create complete linkage
Zd = linkage(distance_matrix,method='complete')
# hierarchical clustering visulization
fig,axs = plt.subplots(1,1,figsize=(25,5))
dn = dendrogram(Zd, truncate_mode='level',p=6,show_leaf_counts=True,ax=axs)
# find optimal k clusters
results = {}
for k in range(2,12):
cluster_array = fcluster(Zd,k,criterion='maxclust')
score = silhouette_score(distance_matrix,cluster_array,metric='precomputed')
results[k] = score
plt.plot([i for i in results.keys()],[j for j in results.values()],label='gower')
from scipy.cluster.hierarchy import fcluster
link = shc.linkage(rez[['Category','Region','Company Age','Number of Employees','6 Month Growth','Number of Investors','Supported Languages','Price Availability','Price Range','Discount for Smallest Package','Discount for Biggest Package','Monthly Subscription','Yearly Subscription','Localization','Customization','Freemium','Free Trial','Number of Versions','Segmentation','Per Feature','Per User','One Time','Pay As You Go','Volume-based Price','Fixed Price']], method='ward')
rez['cluster'] = fcluster(link,10.2,criterion = 'distance')
rez.groupby('cluster').mean()
# In[590]:
import gower
import numpy as np
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import linkage, fcluster, dendrogram
dm = gower.gower_matrix(rez[['Price Availability','Price Range','Discount for Smallest Package','Discount for Biggest Package','Monthly Subscription','Yearly Subscription','Localization','Customization','Freemium','Free Trial','Number of Versions','Segmentation','Per Feature','Per User','One Time','Pay As You Go','Volume-based Price','Fixed Price']])
Zd = linkage(dm)
# In[591]:
plt.figure(figsize=(40, 50), dpi= 80)
plt.title("Дендограмма", fontsize=30)
dendrogram(Zd)
plt.xticks(fontsize=10)
plt.show()
# In[483]:
# combinedDataset_allUsers.csv if the file created for the experiment one from 'output.py'
df = pandas.read_csv(f"{current_directory}\\combinedDataset_allUsers.csv")
df = df.drop(
["level", "temperature", "voltage", "status", "health", "output"],
axis=1) # I want Phone Usage
df["Connectivity"] = df["Cellular"] | df["WiFi"]
df = df.drop(["WiFi", "Cellular", "isInteractive"],
axis=1) # Cause of correlation between columns
# Uncomment for dataframe description #
#print(df.describe())
#plotCorr(df)
# After the first run, you don't have to compute the distance matrix again. You can read it from the pickle file
distance = gower.gower_matrix(df)
with open("distance.pickle", "wb") as f:
pickle.dump(distance, f)
#distance = pickle.load( open( "distance.pickle", "rb" ) )
print("Done with distance!")
del df
# Compute the condensed distance matrix for the linkage and cophenetic
condensedDst = squareform(distance)
#del distance
''' From the linkage function Definition
Methods 'centroid', 'median' and 'ward' are correctly defined only if Euclidean pairwise metric is used. If `y` is passed as precomputed
pairwise distances, then it is a user responsibility to assure that these distances are in fact Euclidean, otherwise the produced result
will be incorrect.
'''
le_dict[col] = deepcopy(le)
nj, nj_bin, nj_ord, nj_categ = compute_nj(train, var_distrib)
nb_cont = np.sum(var_distrib == 'continuous')
# Feature category (cf)
dtype = {
train.columns[j]: dtypes_dict[var_distrib[j]]
for j in range(p)
}
train = train.astype(dtype, copy=True)
numobs = len(train)
# Defining distances over the features
dm = gower_matrix(train, cat_features=cat_features)
#*****************************************************************
# Sampling rules
#*****************************************************************
authorized_ranges = np.expand_dims(
np.stack([[-np.inf, np.inf] for var in var_distrib]).T, 1)
if sub_design == 'bivarié':
# Want to sample only women of more than 60 years old
authorized_ranges[:, 0, 0] = [60,
100] # Of more than 60 years old
# Keep only women
sex_idx = np.argmax(varnames == 'sex')
women_idx = np.argmax(le_dict['sex'].classes_ == 'Female')
def categorical_gower():
print('using categorical data - Gower', end=' ')
categorical_df = pd.DataFrame(gower_matrix(videos_df.loc[:, category_columns], cat_features = [True for v in category_columns])).set_index(videos_df.index)
print('> added {} columns'.format(len(categorical_df.columns)))
return categorical_df
# Feature category (cf)
cf_non_enc = np.logical_or(vd_categ_non_enc == 'categorical',
vd_categ_non_enc == 'bernoulli')
# Non encoded version of the dataset:
#y_nenc_typed = y_categ_non_enc.astype(np.object)
#y_np_nenc = y_nenc_typed.values
dtype = {y.columns[j]: np.float64 if (var_distrib[j] != 'bernoulli') and \
(var_distrib[j] != 'categorical') else str for j in range(p_new)}
y = y.astype(dtype, copy=True)
# !!! Defining distances over the non encoded features
dm = gower_matrix(y, cat_features=cf_non_enc)
#===========================================#
# Running the algorithm
#===========================================#
nb_pobs = 100 # Target for pseudo observations
r = np.array([2, 1])
numobs = len(y)
k = [n_clusters]
seed = 1
init_seed = 2
eps = 1E-05
it = 50
import numpy as np
import gower
from sklearn.neighbors import DistanceMetric
from scipy.sparse import issparse
df = pd.read_csv(
"C:/Users/ahhua/Documents/Github/capstone/Data/processed_data.csv")
df = df.drop([df.columns[0]], axis=1)
df = df.drop(['Title', 'Size', 'Link', 'Filename', 'Src'], axis=1)
cate = [0]
cate.extend([1] * 43)
cate.extend([0, 1, 0, 0, 0, 0])
weights = [2] + (43 * [1]) + (6 * [5])
print('q')
g = gower.gower_matrix(df, weight=np.array(weights), cat_features=cate)
print('r')
pred = gower.gower_topn(df.iloc[0:2, :],
df.iloc[:, ],
n=5,
weight=np.array(weights),
cat_features=cate)
print(pred)
'''
area = DistanceMetric.get_metric('manhattan').pairwise(df[['Area']])
area = area/max(np.ptp(df['Area']),1)
num_colors = DistanceMetric.get_metric('manhattan').pairwise(df[['num_colors']])
num_colors = num_colors/max(np.ptp(df['num_colors']),1)
complexity = DistanceMetric.get_metric('manhattan').pairwise(df[['complexity']])
nan_mask = y.isnull()
cat_features = var_distrib == 'categorical'
y, le_dict = data_processing(y, var_distrib)
y = y.where(~nan_mask, np.nan)
nj, nj_bin, nj_ord, nj_categ = compute_nj(full_contra, var_distrib)
nb_cont = np.sum(var_distrib == 'continuous')
# Feature category (cf)
dtype = {y.columns[j]: dtypes_dict[var_distrib[j]] for j in range(p)}
full_contra = full_contra.astype(dtype, copy=True)
complete_y = y[~y.isna().any(1)].astype(dtype, copy=True)
# Defining distance matrix
dm = gower_matrix(complete_y, cat_features=cat_features)
#===========================================#
# Hyperparameters
#===========================================#
n_clusters = 4
nb_pobs = 100 # Target for pseudo observations
r = np.array([2, 1])
numobs = len(y)
k = [n_clusters]
seed = 1
init_seed = 2
eps = 1E-05
def peptide_identification(args):
print(datetime.now(), ': Peptid identification starts...')
print('Settings: ')
print(args)
# PLATO setting
subclusterCount = args.subclusterCount
spy = args.spy
spy_portion = args.spy_portion
RN = args.RN
rnd_all = args.rnd_all # If random method, include all decoys
rnd_portion = args.rnd_portion # If random method, include rnd.portion of positive set, default 1: pos set = neg set
replicates_cnt = args.replicates_cnt
include_label = args.include_label
AML_preprocess = args.AML_preprocess
output_folder = args.output_folder
# AutoML parameter setting
autoML_best_model_selection = args.autoML_best_model_selection
autoML_iterations = args.autoML_iterations
metric = args.metric # Other metrics: azureml.train.automl.utilities.get_primary_metrics('classification')
cv_fold = args.cv_fold
# Input, output
file_name = args.sample_name
input_path = args.input_folder
output_path = output_folder + '/' + file_name
log_file = output_path + '_autoML_errors_log.html'
# Instantiate AutoML config and create an experiment in autoML workspace
ws = Workspace.from_config()
experiment_name = file_name
experiment = Experiment(ws, experiment_name)
print(datetime.now(),
': Assigned experiment ' + experiment_name + ' on Azure portal ')
output = {}
output['SDK version'] = azureml.core.VERSION
output['Workspace Name'] = ws.name
output['Resource Group'] = ws.resource_group
output['Location'] = ws.location
outputDf = pd.DataFrame(data=output, index=[''])
print(outputDf)
print(datetime.now(), ': Reading inputs')
# Read POSITIVES and ALL inputs
positives_path = glob.glob(input_path + file_name + '*POSITIVES*')
raw_positives = pd.read_csv(positives_path[0], sep='\t')
if AML_preprocess == True:
all_path = glob.glob(input_path + file_name + '-ALL.txt')
raw_all = pd.read_csv(all_path[0], sep='\t')
# Extract new features
# First and last three amino acides of peptide sequences as features - If NA then B category
raw_all['Peptide'] = raw_all.Peptide.str.replace(
r'([\(\[]).*?([\)\]])', r'B', regex=True)
raw_all['P1'] = raw_all['Peptide'].str[0]
raw_all['P2'] = raw_all['Peptide'].str[2]
raw_all['P3'] = raw_all['Peptide'].str[3]
raw_all['P4'] = raw_all['Peptide'].str[-4]
raw_all['P5'] = raw_all['Peptide'].str[-3]
raw_all['P6'] = raw_all['Peptide'].str[-1]
else:
all_path = glob.glob(input_path + file_name +
'_percolator_feature.txt')
raw_all = pd.read_csv(all_path[0], sep='\t')
raw_all['Class'] = 0
# Make positive and test set
test_data = raw_all.drop(['ScanNr', 'Proteins'], axis=1)
positive_set = pd.merge(left=pd.DataFrame(raw_positives['SpecId']),
right=pd.DataFrame(test_data),
how='left',
left_on='SpecId',
right_on='SpecId')
positive_set['Class'] = 1
# Remove decoys in positive set, if there is any
decoys_in_positive_idx = positive_set.index[positive_set['Label'] ==
-1].tolist()
positive_set = positive_set[positive_set['Label'] != -1]
# Dataframe to store predictions
all_predictions = pd.DataFrame({
'SpecId': list(test_data['SpecId']),
'Peptide': list(test_data['Peptide']),
'Label': list(test_data['Label'])
})
prediction_summary = all_predictions
# Prepare test set for modeling
y_test = test_data['Class']
if include_label == True:
X_test = test_data.drop(['SpecId', 'Peptide', 'Class'], axis=1)
else:
X_test = test_data.drop(['SpecId', 'Peptide', 'Label', 'Class'],
axis=1)
# Prepare positive set for modeling
positive_set_idx = [
test_data['SpecId'].tolist().index(x)
for x in positive_set['SpecId'].tolist()
if x in test_data['SpecId'].tolist()
]
# Used to create the negative set
decoys_idx = np.setdiff1d(
test_data.index[test_data['Label'] == -1].tolist(),
decoys_in_positive_idx).tolist()
global gower_dist_avg
if RN == True:
if os.path.exists(input_path + file_name +
'gower_dist_avg.npy') == False:
print(datetime.now(), ': Calculating Gower distance')
gower_dist = gower.gower_matrix(test_data)
selected_rows = gower_dist[positive_set_idx]
gower_dist_avg = np.mean(selected_rows, axis=0)
print(datetime.now(), ': Saving Gower distance matrix')
np.save(input_path + '/' + file_name + 'gower_dist_avg.npy',
gower_dist_avg) # save
else:
print(datetime.now(), ': Loading Gower distance matrix from ',
input_path + file_name + 'gower_dist_avg.npy')
gower_dist_avg = np.load(input_path + file_name +
'gower_dist_avg.npy') # load
if spy == True:
all_spies = pd.DataFrame()
'''
Create train set by concatinating positive and negative set, build model(s) using autoML
and store predictions based on the best model
'''
for rep in range(0, replicates_cnt):
print(datetime.now(), ': Replicate #', rep + 1)
if spy == True:
# Exclude spy_portion of training data to be the spies
positive_set = positive_set.sample(n=len(positive_set),
random_state=rep *
100).reset_index(drop=True)
spySet_size = round(len(positive_set) * spy_portion)
spies_ID = positive_set.loc[1:spySet_size, ['SpecId']]
positive_set_wSpy = positive_set.iloc[spySet_size +
1:len(positive_set)]
if RN == False:
if rnd_all == True:
# Negative set includes all decoys
negative_set_idx = decoys_idx
else:
# Negative set idx includes rnd_portion times of |positive_set| indecies
random.seed(rep)
random.shuffle(decoys_idx)
negative_set_idx = decoys_idx[0:rnd_portion *
len(positive_set)]
else:
print(datetime.now(), ': Starts estimating RNs')
negative_set_idx = reliable_negative(test_data, positive_set,
subclusterCount, rep)
print(datetime.now(), ': Ends estimating RNs')
negative_set = test_data.iloc[negative_set_idx]
if spy == True:
train_data = pd.concat([positive_set_wSpy, negative_set], axis=0)
else:
train_data = pd.concat([positive_set, negative_set], axis=0)
y_train = train_data['Class']
if include_label == True:
X_train = train_data.drop(['SpecId', 'Peptide', 'Class'], axis=1)
else:
X_train = train_data.drop(['SpecId', 'Peptide', 'Class', 'Label'],
axis=1)
print('Training set size:', len(y_train), '\nTest set size:',
len(y_test))
automl_config = AutoMLConfig(task='classification',
debug_log=log_file,
primary_metric=metric,
iteration_timeout_minutes=200,
iterations=autoML_iterations,
verbosity=logging.INFO,
preprocess=AML_preprocess,
X=X_train,
y=y_train,
n_cross_validations=cv_fold,
model_explainability=True)
print(datetime.now(), ': modeling replicate #' + str(rep + 1) + '...')
local_run = experiment.submit(automl_config, show_output=True)
if autoML_best_model_selection == False:
# Retrieve the Best Model based on bunch of metrics
children = list(local_run.get_children())
metricslist = {}
for run in children:
properties = run.get_properties()
metrics = {
k: v
for k, v in run.get_metrics().items()
if isinstance(v, float)
}
metricslist[int(properties['iteration'])] = metrics
rundata = pd.DataFrame(metricslist).sort_index(1)
tmp = rundata.T.sort_values([
'AUC_weighted', 'f1_score_weighted',
'precision_score_weighted', 'recall_score_weighted',
'weighted_accuracy'
],
ascending=False)
rundata = tmp.sort_values('log_loss', ascending=True).T
best_run_iteration = rundata.columns.values[0]
rundata.to_csv(output_path + '_metrics_list_' + str(rep) + '.txt')
best_run, fitted_model = local_run.get_output(
iteration=best_run_iteration)
else:
best_run, fitted_model = local_run.get_output()
print('Best run: ', best_run)
print(datetime.now(), ': Saving best model and predictions')
# Save the best model, prediction value and probability
modelname = output_path + '_model_' + str(rep) + '.sav'
joblib.dump(fitted_model, modelname)
y_pred_val = fitted_model.predict(X_test)
y_pred_prob = fitted_model.predict_proba(X_test)
# Add the results of the replicate to all predictions table
all_predictions['pred_rep' + str(rep)] = list(y_pred_val)
all_predictions['prob_rep' + str(rep)] = list(
[item[1] for item in y_pred_prob])
# Overwrite prediction values based on the spies cutoff
if spy == True:
threshold = min(
pd.merge(spies_ID, all_predictions,
on='SpecId')['prob_rep' + str(rep)])
all_predictions['pred_rep' + str(rep)] = np.where(
all_predictions['prob_rep' + str(rep)] >= threshold, 1, 0)
all_spies['SpecId' + str(rep)] = spies_ID['SpecId']
all_spies['Prob_rep' + str(rep)] = list(
pd.merge(spies_ID, all_predictions,
on=['SpecId'])['prob_rep' + str(rep)])
print(datetime.now(), ': Replicate #' + str(rep + 1) + ' processed!')
all_predictions.to_csv(output_path + '_all_predictions.csv',
index=False)
if spy == True:
all_spies.to_csv(output_path + '_all_spies.csv', index=False)
print(datetime.now(), ': Generate prediction summary of all replicates')
pred_col_indecies = [
col for col in all_predictions.columns if 'pred' in col
]
prob_col_indecies = [
col for col in all_predictions.columns if 'prob' in col
]
prediction_summary['Std'] = all_predictions[prob_col_indecies].std(
skipna=True, axis=1)
prediction_summary['Min'] = all_predictions[prob_col_indecies].min(
skipna=True, axis=1)
prediction_summary['Max'] = all_predictions[prob_col_indecies].max(
skipna=True, axis=1)
prediction_summary['Avg'] = all_predictions[prob_col_indecies].mean(
skipna=True, axis=1)
prediction_summary['Median'] = all_predictions[prob_col_indecies].median(
skipna=True, axis=1)
prediction_summary['Vote'] = all_predictions[pred_col_indecies].sum(
skipna=True, axis=1)
prediction_summary.to_csv(output_path + '_prediction_summary.txt',
sep='\t',
index=False)
# Feature importance
print(datetime.now(), ': Output feature importance of the best run')
client = ExplanationClient.from_run(best_run)
raw_explanations = client.download_model_explanation(
top_k=len(X_test.columns))
print('Raw feature importance')
print(raw_explanations.get_feature_importance_dict())
d = raw_explanations.get_feature_importance_dict()
raw_feature_importance = pd.DataFrame(list(d.items()))
raw_feature_importance.to_csv(output_path + '_raw_feature_importance.csv',
index=False)
# Engineered
engineered_explanations = client.download_model_explanation(
top_k=len(X_test.columns))
print('Engineered feature importance')
print(engineered_explanations.get_feature_importance_dict())
d = engineered_explanations.get_feature_importance_dict()
engineered_feature_importance = pd.DataFrame(list(d.items()))
engineered_feature_importance.to_csv(output_path +
'_engineered_feature_importance.csv',
index=False)
now = datetime.now()
print(datetime.now(), ': Program end')
def get_gower_matrix(self):
distances = gower.gower_matrix(self.data)
distances = pd.DataFrame(distances, index=self.data.index)
distances.columns = distances.index
distances=distances.replace(0, 1000)
return(distances)
import plotly.graph_objects as go
import pandas as pd
import numpy as np
import gower
import prince
from sklearn import manifold
from components import (ALL_STATS, BASIC_STATS, TYPES, GENS, DATA, BASE_COLS,
OTHER, SIZE_COLS, CATEGORICAL_COLS_GOWER,
NUMERICAL_COLS_GOWER)
GOWER_MATRIX = gower.gower_matrix(
DATA.fillna('None')[CATEGORICAL_COLS_GOWER + NUMERICAL_COLS_GOWER])
def update_stats_scatter(stats, types, generations, yaxis):
labels = BASE_COLS + stats + OTHER
df = DATA[labels]
df = df[((df['Type 1'].isin(types)) | (df['Type 2'].isin(types)))
& (df['Generation'].isin(generations))]
df_long = pd.melt(df,
id_vars=BASE_COLS + OTHER,
value_vars=stats,
var_name="Stat")
if len(stats) == 1:
fig = px.scatter(
df,
def DDGMM(y, n_clusters, r, k, init, var_distrib, nj, it = 50, \
eps = 1E-05, maxstep = 100, seed = None, perform_selec = True):
''' Fit a Generalized Linear Mixture of Latent Variables Model (GLMLVM)
y (numobs x p ndarray): The observations containing categorical variables
n_clusters (int): The number of clusters to look for in the data
r (list): The dimension of latent variables through the first 2 layers
k (list): The number of components of the latent Gaussian mixture layers
init (dict): The initialisation parameters for the algorithm
var_distrib (p 1darray): An array containing the types of the variables in y
nj (p 1darray): For binary/count data: The maximum values that the variable can take.
For ordinal data: the number of different existing categories for each variable
it (int): The maximum number of MCEM iterations of the algorithm
eps (float): If the likelihood increase by less than eps then the algorithm stops
maxstep (int): The maximum number of optimisation step for each variable
seed (int): The random state seed to set (Only for numpy generated data for the moment)
perform_selec (Bool): Whether to perform architecture selection or not
------------------------------------------------------------------------------------------------
returns (dict): The predicted classes, the likelihood through the EM steps
and a continuous representation of the data
'''
prev_lik = -1E16
best_lik = -1E16
tol = 0.01
max_patience = 1
patience = 0
best_k = deepcopy(k)
best_r = deepcopy(r)
best_sil = -1
new_sil = -1
# Initialize the parameters
eta = deepcopy(init['eta'])
psi = deepcopy(init['psi'])
lambda_bin = deepcopy(init['lambda_bin'])
lambda_ord = deepcopy(init['lambda_ord'])
lambda_categ = deepcopy(init['lambda_categ'])
H = deepcopy(init['H'])
w_s = deepcopy(
init['w_s']
) # Probability of path s' through the network for all s' in Omega
numobs = len(y)
likelihood = []
it_num = 0
ratio = 1000
np.random.seed = seed
# Dispatch variables between categories
y_bin = y[:,
np.logical_or(var_distrib == 'bernoulli', var_distrib ==
'binomial')]
nj_bin = nj[np.logical_or(var_distrib == 'bernoulli',
var_distrib == 'binomial')].astype(int)
nb_bin = len(nj_bin)
y_categ = y[:, var_distrib == 'categorical']
nj_categ = nj[var_distrib == 'categorical'].astype(int)
nb_categ = len(nj_categ)
y_ord = y[:, var_distrib == 'ordinal']
nj_ord = nj[var_distrib == 'ordinal'].astype(int)
nb_ord = len(nj_ord)
L = len(k)
k_aug = k + [1]
S = np.array([np.prod(k_aug[l:]) for l in range(L + 1)])
M = M_growth(1, r, numobs)
assert nb_ord + nb_bin + nb_categ > 0
# Compute the Gower matrix
cat_features = np.logical_or(var_distrib == 'categorical',
var_distrib == 'bernoulli')
dm = gower_matrix(y, cat_features=cat_features)
while (it_num < it) & ((ratio > eps) | (patience <= max_patience)):
print(it_num)
# The clustering layer is the one used to perform the clustering
# i.e. the layer l such that k[l] == n_clusters
clustering_layer = np.argmax(np.array(k) == n_clusters)
#####################################################################################
################################# S step ############################################
#####################################################################################
#=====================================================================
# Draw from f(z^{l} | s, Theta) for all s in Omega
#=====================================================================
mu_s, sigma_s = compute_path_params(eta, H, psi)
sigma_s = ensure_psd(sigma_s)
z_s, zc_s = draw_z_s(mu_s, sigma_s, eta, M)
'''
print('mu_s', np.abs(mu_s[0]).mean())
print('sigma_s', np.abs(sigma_s[0]).mean())
print('z_s0', np.abs(z_s[0]).mean())
print('z_s1', np.abs(z_s[1]).mean(0)[:,0])
'''
#========================================================================
# Draw from f(z^{l+1} | z^{l}, s, Theta) for l >= 1
#========================================================================
chsi = compute_chsi(H, psi, mu_s, sigma_s)
chsi = ensure_psd(chsi)
rho = compute_rho(eta, H, psi, mu_s, sigma_s, zc_s, chsi)
# In the following z2 and z1 will denote z^{l+1} and z^{l} respectively
z2_z1s = draw_z2_z1s(chsi, rho, M, r)
#=======================================================================
# Compute the p(y| z1) for all variable categories
#=======================================================================
py_zl1 = fy_zl1(lambda_bin, y_bin, nj_bin, lambda_ord, y_ord, nj_ord,
lambda_categ, y_categ, nj_categ, z_s[0])
#========================================================================
# Draw from p(z1 | y, s) proportional to p(y | z1) * p(z1 | s) for all s
#========================================================================
zl1_ys = draw_zl1_ys(z_s, py_zl1, M)
#####################################################################################
################################# E step ############################################
#####################################################################################
#=====================================================================
# Compute conditional probabilities used in the appendix of asta paper
#=====================================================================
pzl1_ys, ps_y, p_y = E_step_GLLVM(z_s[0], mu_s[0], sigma_s[0], w_s,
py_zl1)
#del(py_zl1)
#=====================================================================
# Compute p(z^{(l)}| s, y). Equation (5) of the paper
#=====================================================================
pz2_z1s = fz2_z1s(t(pzl1_ys, (1, 0, 2)), z2_z1s, chsi, rho, S)
pz_ys = fz_ys(t(pzl1_ys, (1, 0, 2)), pz2_z1s)
#=====================================================================
# Compute MFA expectations
#=====================================================================
Ez_ys, E_z1z2T_ys, E_z2z2T_ys, EeeT_ys = \
E_step_DGMM(zl1_ys, H, z_s, zc_s, z2_z1s, pz_ys, pz2_z1s, S)
###########################################################################
############################ M step #######################################
###########################################################################
#=======================================================
# Compute MFA Parameters
#=======================================================
w_s = np.mean(ps_y, axis=0)
eta, H, psi = M_step_DGMM(Ez_ys, E_z1z2T_ys, E_z2z2T_ys, EeeT_ys, ps_y,
H, k)
#=======================================================
# Identifiability conditions
#=======================================================
# Update eta, H and Psi values
H = diagonal_cond(H, psi)
Ez, AT = compute_z_moments(w_s, eta, H, psi)
eta, H, psi = identifiable_estim_DGMM(eta, H, psi, Ez, AT)
del (Ez)
#=======================================================
# Compute GLLVM Parameters
#=======================================================
# We optimize each column separately as it is faster than all column jointly
# (and more relevant with the independence hypothesis)
lambda_bin = bin_params_GLLVM(y_bin, nj_bin, lambda_bin, ps_y, pzl1_ys, z_s[0], AT[0],\
tol = tol, maxstep = maxstep)
lambda_ord = ord_params_GLLVM(y_ord, nj_ord, lambda_ord, ps_y, pzl1_ys, z_s[0], AT[0],\
tol = tol, maxstep = maxstep)
lambda_categ = categ_params_GLLVM(y_categ, nj_categ, lambda_categ, ps_y, pzl1_ys, z_s[0], AT[0],\
tol = tol, maxstep = maxstep)
###########################################################################
################## Clustering parameters updating #########################
###########################################################################
new_lik = np.sum(np.log(p_y))
likelihood.append(new_lik)
ratio = (new_lik - prev_lik) / abs(prev_lik)
print(likelihood)
idx_to_sum = tuple(set(range(1, L + 1)) - set([clustering_layer + 1]))
psl_y = ps_y.reshape(numobs, *k, order='C').sum(idx_to_sum)
temp_class = np.argmax(psl_y, axis=1)
try:
new_sil = silhouette_score(dm, temp_class, metric='precomputed')
except ValueError:
new_sil = -1
print('Silhouette score:', new_sil)
if best_sil < new_sil:
z = (ps_y[..., n_axis] * Ez_ys[clustering_layer]).sum(1)
best_sil = deepcopy(new_sil)
classes = deepcopy(temp_class)
fig = plt.figure(figsize=(8, 8))
plt.scatter(z[:, 0], z[:, 1])
plt.show()
# Refresh the classes only if they provide a better explanation of the data
if best_lik < new_lik:
best_lik = deepcopy(prev_lik)
if prev_lik < new_lik:
patience = 0
M = M_growth(it_num + 2, r, numobs)
else:
patience += 1
###########################################################################
######################## Parameter selection #############################
###########################################################################
is_not_min_specif = not (np.all(np.array(k) == n_clusters)
& np.array_equal(r, [2, 1]))
if look_for_simpler_network(
it_num) & perform_selec & is_not_min_specif:
r_to_keep = r_select(y_bin, y_ord, y_categ, zl1_ys, z2_z1s, w_s)
# If r_l == 0, delete the last l + 1: layers
new_L = np.sum([len(rl) != 0 for rl in r_to_keep]) - 1
k_to_keep = k_select(w_s, k, new_L, clustering_layer)
is_L_unchanged = L == new_L
is_r_unchanged = np.all(
[len(r_to_keep[l]) == r[l] for l in range(new_L + 1)])
is_k_unchanged = np.all(
[len(k_to_keep[l]) == k[l] for l in range(new_L)])
is_selection = not (is_r_unchanged & is_k_unchanged
& is_L_unchanged)
assert new_L > 0
if is_selection:
eta = [eta[l][k_to_keep[l]] for l in range(new_L)]
eta = [eta[l][:, r_to_keep[l]] for l in range(new_L)]
H = [H[l][k_to_keep[l]] for l in range(new_L)]
H = [H[l][:, r_to_keep[l]] for l in range(new_L)]
H = [H[l][:, :, r_to_keep[l + 1]] for l in range(new_L)]
psi = [psi[l][k_to_keep[l]] for l in range(new_L)]
psi = [psi[l][:, r_to_keep[l]] for l in range(new_L)]
psi = [psi[l][:, :, r_to_keep[l]] for l in range(new_L)]
if nb_bin > 0:
# Add the intercept:
bin_r_to_keep = np.concatenate([[0],
np.array(r_to_keep[0]) + 1
])
lambda_bin = lambda_bin[:, bin_r_to_keep]
if nb_ord > 0:
# Intercept coefficients handling is a little more complicated here
lambda_ord_intercept = [
lambda_ord_j[:-r[0]] for lambda_ord_j in lambda_ord
]
Lambda_ord_var = np.stack(
[lambda_ord_j[-r[0]:] for lambda_ord_j in lambda_ord])
Lambda_ord_var = Lambda_ord_var[:, r_to_keep[0]]
lambda_ord = [np.concatenate([lambda_ord_intercept[j], Lambda_ord_var[j]])\
for j in range(nb_ord)]
if nb_categ > 0:
lambda_categ_intercept = [
lambda_categ[j][:, 0] for j in range(nb_categ)
]
Lambda_categ_var = [
lambda_categ_j[:, -r[0]:]
for lambda_categ_j in lambda_categ
]
Lambda_categ_var = [
lambda_categ_j[:, r_to_keep[0]]
for lambda_categ_j in lambda_categ
]
lambda_categ = [np.hstack([lambda_categ_intercept[j][..., n_axis], Lambda_categ_var[j]])\
for j in range(nb_categ)]
w = w_s.reshape(*k, order='C')
new_k_idx_grid = np.ix_(*k_to_keep[:new_L])
# If layer deletion, sum the last components of the paths
if L > new_L:
deleted_dims = tuple(range(L)[new_L:])
w_s = w[new_k_idx_grid].sum(deleted_dims).flatten(
order='C')
else:
w_s = w[new_k_idx_grid].flatten(order='C')
w_s /= w_s.sum()
k = [len(k_to_keep[l]) for l in range(new_L)]
r = [len(r_to_keep[l]) for l in range(new_L + 1)]
k_aug = k + [1]
S = np.array([np.prod(k_aug[l:]) for l in range(new_L + 1)])
L = new_L
patience = 0
best_r = deepcopy(r)
best_k = deepcopy(k)
# Identifiability conditions
H = diagonal_cond(H, psi)
Ez, AT = compute_z_moments(w_s, eta, H, psi)
eta, H, psi = identifiable_estim_DGMM(eta, H, psi, Ez, AT)
print('New architecture:')
print('k', k)
print('r', r)
print('L', L)
print('S', S)
print("w_s", len(w_s))
prev_lik = deepcopy(new_lik)
it_num = it_num + 1
out = dict(likelihood = likelihood, classes = classes, z = z, \
best_r = best_r, best_k = best_k)
return (out)
def post(self,request):
# request = self.request.data
null=np.nan
# stores = request['data']['teststores']
# ########
filename = request.FILES['store_mstr']
if filename:
filename_check = filename.name
ext = [".xlsx", ".csv", ".xls"]
if filename_check.endswith(tuple(ext)):
extesnion = os.path.splitext(filename_check)[1]
if (extesnion == '.csv'):
data = pd.read_csv(filename)
else:
teststores = pd.read_excel(filename)
store_features =request.POST['store_features']
# stores =request.POST['teststores']
##############
# stores = pd.DataFrame(eval(stores))
# teststores = pd.DataFrame.from_dict(stores, orient='columns')
# store_features =request['data']['store_features']
if teststores is not None:
mandatory_features = ['Banner', 'Outlet_surface', 'Shelf_meters_Choc','Shelf_meters_Dog', 'Shelf_meters_Cat',
'Influence_Overall','CSV_of_outlet']
# store_features = mandatory_features + store_features
# stores_master_df = pd.read_excel("datas/TL_StoreMstr.xlsx")
# test_master_df = pd.read_excel("TL_TestMstr.xlsx")
# teststore_map_df = pd.read_excel("TL_Teststore_map.xlsx")
# controlstore_map_df = pd.read_excel("TL_Controlstore_Mstr.xlsx")
Allstores = StoreMstr.objects.filter(is_active=True,is_deleted=False)
Teststores = TestStoreSerializer(Allstores,many=True)
stores_master_df = pd.DataFrame(Teststores.data)
Alltest = TestMstr.objects.filter(is_active=True,is_deleted=False)
Testmst = TestSerializer(Alltest,many=True)
test_master_df = pd.DataFrame(Testmst.data)
# test_master_df = pd.read_excel("datas/TL_TestMstr.xlsx")
if(test_master_df.empty):
columns = ['test_id','test_name','test_desc','testtype','target_var','territory_name','store_segment','category_name','confidence_lev','margin_oferror','std_deviation','pre_start','pre_end','test_window','testwin_start','testwin_end','stage_id','created_on','modified_on','is_active','deleted_at','is_deleted']
test_master_df = pd.DataFrame(columns=columns)
Alltestmap = TestStoreMap.objects.filter(is_active=True,is_deleted=False)
Teststop = TestStoreMapSerializer(Alltestmap,many=True)
teststore_map_df = pd.DataFrame(Teststop.data)
# teststore_map_df = pd.read_excel("datas/TL_Teststore_map.xlsx")
controlstore = ControlStoreMstr.objects.filter(is_active=True,is_deleted=False)
controlstores = ControlstoreSerializer(controlstore,many=True)
controlstore_map_df = pd.DataFrame(Teststop.data)
# Eliminating the Invalid Stores From Population
stores_master_df = check_if_store_valid(storesfile=stores_master_df)
stores_master_df = stores_master_df[stores_master_df["Is Valid Store"]==1]
# ELIMINATING ALL THE TEST AND CONTROL STORES WHICH ARE CURRENTLY ACTIVE
# Get all the active tests(test ids)
active_tests_df = test_master_df[test_master_df["is_active"]==True]
if active_tests_df.shape[0] != 0:
# THIS MEANS THERE ARE ACTIVE TESTS AND WE NEED TO ELIMINATE ACTIVE TEST AND CONTROL STORES
#Get the active test stores using test ids
active_test_stores = teststore_map_df[teststore_map_df["test_id"].isin(active_tests_df["test_id"])]
#Get the active control stores using test ids
active_control_stores = controlstore_map_df[controlstore_map_df["test_id"].isin(active_tests_df["test_id"])]
#Remove active test and control stores from population
stores_master_df = stores_master_df[~stores_master_df["store_id"].isin(active_test_stores["store_id"])]
stores_master_df = stores_master_df[~stores_master_df["store_id"].isin(active_control_stores["store_id"])]
else:
# THIS MEANS THERE ARE NO ACTIVE TESTS AND WE NEED NOT ELIMINATE ANY TEST AND CONTROL STORES
pass
# ELIMINATING THE TESTSTORES FROM POPULATION
stores_master_df = stores_master_df[~(stores_master_df["Partner_ID"].isin(teststores["Partner_ID"]))]
refA = teststores.copy(deep=True)
refB = stores_master_df.copy(deep=True)
useA = refA[store_features].copy(deep=True)
useB = refB[store_features].copy(deep=True)
scaler = StandardScaler()
scale_cols = [item for item in store_features if item!="Banner"]
useA[scale_cols] = scaler.fit_transform(useA[scale_cols])
useB[scale_cols] = scaler.fit_transform(useB[scale_cols])
gowermatrix = gower.gower_matrix(useA,useB)
# Identifying similar stores
df_list = list()
for test_pid,row in zip(refA["Partner ID"],gowermatrix):
df = refB.copy(deep=True)
df["Gower_Distance"] = list(row)
df = df.sort_values(by="Gower_Distance",ascending=True)
df["Test store Partner ID"] = test_pid
df["Gower_Distance"] = df["Gower_Distance"].apply(lambda x:round(x,2))
df["Similarity Measure"] = df["Gower_Distance"].apply(lambda x: 1-x)
df_list.append(df.head(1))
control_stores = pd.concat(df_list)
control_stores["Checked_Flag"] = 0
finalcontrol_stores = control_stores.reset_index().to_json(orient='records')
return json.Response(finalcontrol_stores,True)
else:
return json.Response("Please pass Test stores",False)
cluster_telco_centroid = pd.Series(telco_centroid.labels_)
telco_data["cluster"] = cluster_telco_centroid
telco_data.iloc[:, 0:29].groupby(telco_data.cluster).mean()
import os
telco_data.to_csv("final_telco_data.csv", encoding="utf-8")
os.getcwd()
#using gowers clustering for mixed data
import gower
from scipy.cluster.hierarchy import fcluster, dendrogram
gowers_matrix = gower.gower_matrix(telco_data)
gowers_linkage = linkage(gowers_matrix)
gcluster = fcluster(gowers_linkage, 3, criterion='maxclust')
dendrogram(gowers_linkage)
telco_data["cluster"] = gcluster
telco_data.iloc[:, 0:29].groupby(telco_data.cluster).mean()
import os
telco_data.to_csv("final2_telco_data.csv", encoding="utf-8")
os.getcwd()
#############################Problem 4####################################################
import pandas as pd
def MDGMM(y, n_clusters, r, k, init, var_distrib, nj, it = 50, \
eps = 1E-05, maxstep = 100, seed = None, perform_selec = True):
''' Fit a Generalized Linear Mixture of Latent Variables Model (GLMLVM)
y (numobs x p ndarray): The observations containing mixed variables
n_clusters (int or str): The number of clusters to look for in the data or the use mode of the MDGMM
r (dict): The dimension of latent variables through the first 2 layers
k (dict): The number of components of the latent Gaussian mixture layers
init (dict): The initialisation parameters for the algorithm
var_distrib (p 1darray): An array containing the types of the variables in y
nj (p 1darray): For binary/count data: The maximum values that the variable can take.
For ordinal data: the number of different existing categories for each variable
For categorical data: the number of different existing categories for each variable
it (int): The maximum number of MCEM iterations of the algorithm
eps (float): If the likelihood increase by less than eps then the algorithm stops
maxstep (int): The maximum number of optimisation step for each variable
seed (int): The random state seed to set (Only for numpy generated data for the moment)
perform_selec (Bool): Whether to perform architecture selection or not
------------------------------------------------------------------------------------------------
returns (dict): The predicted classes, the likelihood through the EM steps
and a continuous representation of the data
'''
# Break the reference link
k = deepcopy(k)
r = deepcopy(r)
best_k = deepcopy(k)
best_r = deepcopy(r)
# Add other checks for the other variables
check_inputs(k, r)
prev_lik = - 1E15
best_lik = -1E15
tol = 0.01
max_patience = 1
patience = 0
#====================================================
# Initialize the parameters
#====================================================
eta_c, eta_d, H_c, H_d, psi_c, psi_d = dispatch_dgmm_init(init)
lambda_bin, lambda_ord, lambda_categ = dispatch_gllvm_init(init)
w_s_c, w_s_d = dispatch_paths_init(init)
numobs = len(y)
likelihood = []
it_num = 0
ratio = 1000
np.random.seed = seed
#====================================================
# Dispatch variables between categories
#====================================================
y_bin = y[:, np.logical_or(var_distrib == 'bernoulli',\
var_distrib == 'binomial')]
nj_bin = nj[np.logical_or(var_distrib == 'bernoulli',\
var_distrib == 'binomial')]
nj_bin = nj_bin.astype(int)
nb_bin = len(nj_bin)
y_ord = y[:, var_distrib == 'ordinal']
nj_ord = nj[var_distrib == 'ordinal']
nj_ord = nj_ord.astype(int)
nb_ord = len(nj_ord)
y_categ = y[:, var_distrib == 'categorical']
nj_categ = nj[var_distrib == 'categorical'].astype(int)
nb_categ = len(nj_categ)
yc = y[:, var_distrib == 'continuous']
ss = StandardScaler()
yc = ss.fit_transform(yc)
nb_cont = yc.shape[1]
# *_1L standsds for quantities going through all the network (head + tail)
k_1L, L_1L, L, bar_L, S_1L = nb_comps_and_layers(k)
r_1L = {'c': r['c'] + r['t'], 'd': r['d'] + r['t'], 't': r['t']}
best_sil = [-1.1 for l in range(L['t'] - 1)] if n_clusters == 'multi' else -1.1
new_sil = [-1.1 for l in range(L['t'] - 1)] if n_clusters == 'multi' else -1.1
M = M_growth(1, r_1L, numobs)
if nb_bin + nb_ord + nb_categ == 0: # Create the InputError class and change this
raise ValueError('Input does not contain discrete variables,\
consider using a regular DGMM')
if nb_cont == 0: # Create the InputError class and change this
raise ValueError('Input does not contain continuous values,\
consider using a DDGMM')
# Compute the Gower matrix
cat_features = np.logical_or(var_distrib == 'categorical', var_distrib == 'bernoulli')
dm = gower_matrix(y, cat_features = cat_features)
while (it_num < it) & ((ratio > eps) | (patience <= max_patience)):
print(it_num)
# The clustering layer is the one used to perform the clustering
# i.e. the layer l such that k[l] == n_clusters
if not(isnumeric(n_clusters)):
if n_clusters == 'auto':
clustering_layer = 0
elif n_clusters == 'multi':
clustering_layer = list(range(L['t'] - 1))
else:
raise ValueError('Please enter an int, auto or multi for n_clusters')
else:
assert (np.array(k['t']) == n_clusters).any()
clustering_layer = np.argmax(np.array(k['t']) == n_clusters)
#####################################################################################
################################# MC step ############################################
#####################################################################################
#=====================================================================
# Draw from f(z^{l} | s, Theta) for both heads and tail
#=====================================================================
mu_s_c, sigma_s_c = compute_path_params(eta_c, H_c, psi_c)
sigma_s_c = ensure_psd(sigma_s_c)
mu_s_d, sigma_s_d = compute_path_params(eta_d, H_d, psi_d)
sigma_s_d = ensure_psd(sigma_s_d)
z_s_c, zc_s_c, z_s_d, zc_s_d = draw_z_s_all_network(mu_s_c, sigma_s_c,\
mu_s_d, sigma_s_d, yc, eta_c, eta_d, S_1L, L, M)
#========================================================================
# Draw from f(z^{l+1} | z^{l}, s, Theta) for l >= 1
#========================================================================
# Create wrapper as before and after
chsi_c = compute_chsi(H_c, psi_c, mu_s_c, sigma_s_c)
chsi_c = ensure_psd(chsi_c)
rho_c = compute_rho(eta_c, H_c, psi_c, mu_s_c, sigma_s_c, zc_s_c, chsi_c)
chsi_d = compute_chsi(H_d, psi_d, mu_s_d, sigma_s_d)
chsi_d = ensure_psd(chsi_d)
rho_d = compute_rho(eta_d, H_d, psi_d, mu_s_d, sigma_s_d, zc_s_d, chsi_d)
# In the following z2 and z1 will denote z^{l+1} and z^{l} respectively
z2_z1s_c, z2_z1s_d = draw_z2_z1s_network(chsi_c, chsi_d, rho_c, \
rho_d, M, r_1L, L)
#=======================================================================
# Compute the p(y^D| z1) for all discrete variables
#=======================================================================
py_zl1_d = fy_zl1(lambda_bin, y_bin, nj_bin, lambda_ord, y_ord, nj_ord,\
lambda_categ, y_categ, nj_categ, z_s_d[0])
#========================================================================
# Draw from p(z1 | y, s) proportional to p(y | z1) * p(z1 | s) for all s
#========================================================================
zl1_ys_d = draw_zl1_ys(z_s_d, py_zl1_d, M['d'])
#####################################################################################
################################# E step ############################################
#####################################################################################
#=====================================================================
# Compute quantities necessary for E steps of both heads and tail
#=====================================================================
# Discrete head quantities
pzl1_ys_d, ps_y_d, py_d = E_step_GLLVM(z_s_d[0], mu_s_d[0], sigma_s_d[0], w_s_d, py_zl1_d)
py_s_d = ps_y_d * py_d / w_s_d[n_axis]
# Continuous head quantities
ps_y_c, py_s_c, py_c = continuous_lik(yc, mu_s_c[0], sigma_s_c[0], w_s_c)
pz_s_d = fz_s(z_s_d, mu_s_d, sigma_s_d)
pz_s_c = fz_s(z_s_c, mu_s_c, sigma_s_c)
#=====================================================================
# Compute p(z^{(l)}| s, y). Equation (5) of the paper
#=====================================================================
# Compute pz2_z1s_d and pz2_z1s_d for the tail indices whereas it is useless
pz2_z1s_d = fz2_z1s(t(pzl1_ys_d, (1, 0, 2)), z2_z1s_d, chsi_d, rho_d, S_1L['d'])
pz_ys_d = fz_ys(t(pzl1_ys_d, (1, 0, 2)), pz2_z1s_d)
pz2_z1s_c = fz2_z1s([], z2_z1s_c, chsi_c, rho_c, S_1L['c'])
pz_ys_c = fz_ys([], pz2_z1s_c)
pz2_z1s_t = fz2_z1s([], z2_z1s_c[bar_L['c']:], chsi_c[bar_L['c']:], \
rho_c[bar_L['c']:], S_1L['t'])
# Junction layer computations
# Compute p(zC |s)
py_zs_d = fy_zs(pz_ys_d, py_s_d)
py_zs_c = fy_zs(pz_ys_c, py_s_c)
# Compute p(zt | yC, yD, sC, SD)
pzt_yCyDs = fz_yCyDs(py_zs_c, pz_ys_d, py_s_c, M, S_1L, L)
#=====================================================================
# Compute MFA expectations
#=====================================================================
# Discrete head.
Ez_ys_d, E_z1z2T_ys_d, E_z2z2T_ys_d, EeeT_ys_d = \
E_step_DGMM_d(zl1_ys_d, H_d, z_s_d, zc_s_d, z2_z1s_d, pz_ys_d,\
pz2_z1s_d, S_1L['d'], L['d'])
# Continuous head
Ez_ys_c, E_z1z2T_ys_c, E_z2z2T_ys_c, EeeT_ys_c = \
E_step_DGMM_c(H_c, z_s_c, zc_s_c, z2_z1s_c, pz_ys_c,\
pz2_z1s_c, S_1L['c'], L['c'])
# Junction layers
Ez_ys_t, E_z1z2T_ys_t, E_z2z2T_ys_t, EeeT_ys_t = \
E_step_DGMM_t(H_c[bar_L['c']:], \
z_s_c[bar_L['c']:], zc_s_c[bar_L['c']:], z2_z1s_c[bar_L['c']:],\
pzt_yCyDs, pz2_z1s_t, S_1L, L, k_1L)
# Error here for the first two terms: p(y^h | z^t, s^C) != p(y^h | z^t, s^{1C:L})
pst_yCyD = fst_yCyD(py_zs_c, py_zs_d, pz_s_d, w_s_c, w_s_d, k_1L, L)
###########################################################################
############################ M step #######################################
###########################################################################
#=======================================================
# Compute DGMM Parameters
#=======================================================
# Discrete head
w_s_d = np.mean(ps_y_d, axis = 0)
eta_d_barL, H_d_barL, psi_d_barL = M_step_DGMM(Ez_ys_d, E_z1z2T_ys_d, E_z2z2T_ys_d, \
EeeT_ys_d, ps_y_d, H_d, k_1L['d'][:-1],\
L_1L['d'], r_1L['d'])
# Add dispatching function here
eta_d[:bar_L['d']] = eta_d_barL
H_d[:bar_L['d']] = H_d_barL
psi_d[:bar_L['d']] = psi_d_barL
# Continuous head
w_s_c = np.mean(ps_y_c, axis = 0)
eta_c_barL, H_c_barL, psi_c_barL = M_step_DGMM(Ez_ys_c, E_z1z2T_ys_c, E_z2z2T_ys_c, \
EeeT_ys_c, ps_y_c, H_c, k_1L['c'][:-1],\
L_1L['c'] + 1, r_1L['c'])
eta_c[:bar_L['c']] = eta_c_barL
H_c[:bar_L['c']] = H_c_barL
psi_c[:bar_L['c']] = psi_c_barL
# Common tail
eta_t, H_t, psi_t, Ezst_y = M_step_DGMM_t(Ez_ys_t, E_z1z2T_ys_t, E_z2z2T_ys_t, \
EeeT_ys_t, ps_y_c, ps_y_d, pst_yCyD, \
H_c[bar_L['c']:], S_1L, k_1L, \
L_1L, L, r_1L['t'])
eta_d[bar_L['d']:] = eta_t
H_d[bar_L['d']:] = H_t
psi_d[bar_L['d']:] = psi_t
eta_c[bar_L['c']:] = eta_t
H_c[bar_L['c']:] = H_t
psi_c[bar_L['c']:] = psi_t
#=======================================================
# Identifiability conditions
#=======================================================
w_s_t = np.mean(pst_yCyD, axis = 0)
eta_d, H_d, psi_d, AT_d, eta_c, H_c, psi_c, AT_c = network_identifiability(eta_d, \
H_d, psi_d, eta_c, H_c, psi_c, w_s_c, w_s_d, w_s_t, bar_L)
#=======================================================
# Compute GLLVM Parameters
#=======================================================
# We optimize each column separately as it is faster than all column jointly
# (and more relevant with the independence hypothesis)
lambda_bin = bin_params_GLLVM(y_bin, nj_bin, lambda_bin, ps_y_d, \
pzl1_ys_d, z_s_d[0], AT_d[0], tol = tol, maxstep = maxstep)
lambda_ord = ord_params_GLLVM(y_ord, nj_ord, lambda_ord, ps_y_d, \
pzl1_ys_d, z_s_d[0], AT_d[0], tol = tol, maxstep = maxstep)
lambda_categ = categ_params_GLLVM(y_categ, nj_categ, lambda_categ, ps_y_d,\
pzl1_ys_d, z_s_d[0], AT_d[0], tol = tol, maxstep = maxstep)
###########################################################################
################## Clustering parameters updating #########################
###########################################################################
new_lik = np.sum(np.log(py_d) + np.log(py_c))
likelihood.append(new_lik)
ratio = (new_lik - prev_lik)/abs(prev_lik)
if n_clusters == 'multi':
temp_classes = []
z_tail = []
classes = [[] for l in range(L['t'] - 1)]
for l in clustering_layer:
idx_to_sum = tuple(set(range(1, L['t'] + 1)) -\
set([clustering_layer[l] + 1]))
psl_y = pst_yCyD.reshape(numobs, *k['t'],\
order = 'C').sum(idx_to_sum)
temp_class_l = np.argmax(psl_y, axis = 1)
sil_l = silhouette_score(dm, temp_class_l, metric = 'precomputed')
temp_classes.append(temp_class_l)
#z_tail.append(Ezst_y[l].sum(1))
new_sil[l] = sil_l
#z_tail = []
for l in range(L['t'] - 1):
zl = Ezst_y[l].sum(1)
z_tail.append(zl)
if best_sil[l] < new_sil[l]:
# Update the quantity if the silhouette score is better
best_sil[l] = deepcopy(new_sil[l])
classes[l] = deepcopy(temp_classes[l])
if zl.shape[-1] == 3:
plot_3d(zl, classes[l])
elif zl.shape[-1] == 2:
plot_2d(zl, classes[l])
else:
idx_to_sum = tuple(set(range(1, L['t'] + 1)) - set([clustering_layer + 1]))
psl_y = pst_yCyD.reshape(numobs, *k['t'], order = 'C').sum(idx_to_sum)
temp_classes = np.argmax(psl_y, axis = 1)
try:
new_sil = silhouette_score(dm, temp_classes, metric = 'precomputed')
except:
new_sil = -1
z_tail = [Ezst_y[l].sum(1) for l in range(L['t'] - 1)]
if best_sil < new_sil:
# Update the quantity if the silhouette score is better
zl = z_tail[clustering_layer]
best_sil = deepcopy(new_sil)
classes = deepcopy(temp_classes)
if zl.shape[-1] == 3:
plot_3d(zl, classes)
elif zl.shape[-1] == 2:
plot_2d(zl, classes)
# Refresh the likelihood if best
if best_lik < new_lik:
best_lik = deepcopy(prev_lik)
if prev_lik < new_lik:
patience = 0
M = M_growth(it_num + 1, r_1L, numobs)
else:
patience += 1
###########################################################################
######################## Parameter selection #############################
###########################################################################
min_nb_clusters = 2
is_not_min_specif = not(is_min_architecture_reached(k, r, min_nb_clusters))
if look_for_simpler_network(it_num) & perform_selec & is_not_min_specif:
# To add: selection according to categ
r_to_keep = r_select(y_bin, y_ord, y_categ, yc, zl1_ys_d,\
z2_z1s_d[:bar_L['d']], w_s_d, z2_z1s_c[:bar_L['c']],
z2_z1s_c[bar_L['c']:], n_clusters)
# Check layer deletion
is_c_layer_deletion = np.any([len(rl) == 0 for rl in r_to_keep['c']])
is_d_layer_deletion = np.any([len(rl) == 0 for rl in r_to_keep['d']])
is_head_layer_deletion = np.any([is_c_layer_deletion, is_d_layer_deletion])
if is_head_layer_deletion:
# Restart the algorithm
if is_c_layer_deletion:
r['c'] = [len(rl) for rl in r_to_keep['c'][:-1]]
k['c'] = k['c'][:-1]
if is_d_layer_deletion:
r['d'] = [len(rl) for rl in r_to_keep['d'][:-1]]
k['d'] = k['d'][:-1]
init = dim_reduce_init(pd.DataFrame(y), n_clusters, k, r, nj, var_distrib,\
seed = None)
eta_c, eta_d, H_c, H_d, psi_c, psi_d = dispatch_dgmm_init(init)
lambda_bin, lambda_ord, lambda_categ = dispatch_gllvm_init(init)
w_s_c, w_s_d = dispatch_paths_init(init)
# *_1L standsds for quantities going through all the network (head + tail)
k_1L, L_1L, L, bar_L, S_1L = nb_comps_and_layers(k)
r_1L = {'c': r['c'] + r['t'], 'd': r['d'] + r['t'], 't': r['t']}
M = M_growth(it_num + 1, r_1L, numobs)
prev_lik = deepcopy(new_lik)
it_num = it_num + 1
print(likelihood)
print('Restarting the algorithm')
continue
new_Lt = np.sum([len(rl) != 0 for rl in r_to_keep['t']]) #- 1
# If r_l == 0, delete the last l + 1: layers
new_Lt = np.sum([len(rl) != 0 for rl in r_to_keep['t']]) #- 1
#w_s_t = pst_yCyD.mean(0)
k_to_keep = k_select(w_s_c, w_s_d, w_s_t, k, new_Lt, clustering_layer, n_clusters)
is_selection = check_if_selection(r_to_keep, r, k_to_keep, k, L, new_Lt)
assert new_Lt > 0 # > 1 ?
if n_clusters == 'multi':
assert new_Lt == L['t']
if is_selection:
# Part to change when update also number of layers on each head
nb_deleted_layers_tail = L['t'] - new_Lt
L['t'] = new_Lt
L_1L = {keys: values - nb_deleted_layers_tail for keys, values in L_1L.items()}
eta_c, eta_d, H_c, H_d, psi_c, psi_d = dgmm_coeff_selection(eta_c,\
H_c, psi_c, eta_d, H_d, psi_d, L, r_to_keep, k_to_keep)
lambda_bin, lambda_ord, lambda_categ = gllvm_coeff_selection(lambda_bin, lambda_ord,\
lambda_categ, r, r_to_keep)
w_s_c, w_s_d = path_proba_selection(w_s_c, w_s_d, k, k_to_keep, new_Lt)
k = {h: [len(k_to_keep[h][l]) for l in range(L[h])] for h in ['d', 't']}
k['c'] = [len(k_to_keep['c'][l]) for l in range(L['c'] + 1)]
r = {h: [len(r_to_keep[h][l]) for l in range(L[h])] for h in ['d', 't']}
r['c'] = [len(r_to_keep['c'][l]) for l in range(L['c'] + 1)]
k_1L, _, L, bar_L, S_1L = nb_comps_and_layers(k)
r_1L = {'c': r['c'] + r['t'], 'd': r['d'] + r['t'], 't': r['t']}
patience = 0
best_r = deepcopy(r)
best_k = deepcopy(k)
#=======================================================
# Identifiability conditions
#=======================================================
eta_d, H_d, psi_d, AT_d, eta_c, H_c, psi_c, AT_c = network_identifiability(eta_d, \
H_d, psi_d, eta_c, H_c, psi_c, w_s_c, w_s_d, w_s_t, bar_L)
print('New architecture:')
print('k', k)
print('r', r)
print('L', L)
print('S_1L', S_1L)
print("w_s_c", len(w_s_c))
print("w_s_d", len(w_s_d))
M = M_growth(it_num + 1, r_1L, numobs)
prev_lik = deepcopy(new_lik)
print(likelihood)
print('Silhouette score:', new_sil)
it_num = it_num + 1
out = dict(likelihood = likelihood, classes = classes, \
best_r = best_r, best_k = best_k)
if n_clusters == 'multi':
out['z'] = z_tail
else:
out['z'] = z_tail[clustering_layer]
return(out)
def M1DGMM(y, n_clusters, r, k, init, var_distrib, nj, it = 50, \
eps = 1E-05, maxstep = 100, seed = None, perform_selec = True,\
dm = [], max_patience = 1, use_silhouette = True):# dm small hack to remove
''' Fit a Generalized Linear Mixture of Latent Variables Model (GLMLVM)
y (numobs x p ndarray): The observations containing mixed variables
n_clusters (int): The number of clusters to look for in the data
r (list): The dimension of latent variables through the first 2 layers
k (list): The number of components of the latent Gaussian mixture layers
init (dict): The initialisation parameters for the algorithm
var_distrib (p 1darray): An array containing the types of the variables in y
nj (p 1darray): For binary/count data: The maximum values that the variable can take.
For ordinal data: the number of different existing categories for each variable
it (int): The maximum number of MCEM iterations of the algorithm
eps (float): If the likelihood increase by less than eps then the algorithm stops
maxstep (int): The maximum number of optimisation step for each variable
seed (int): The random state seed to set (Only for numpy generated data for the moment)
perform_selec (Bool): Whether to perform architecture selection or not
use_silhouette (Bool): If True use the silhouette as quality criterion (best for clustering) else use
the likelihood (best for data augmentation).
------------------------------------------------------------------------------------------------
returns (dict): The predicted classes, the likelihood through the EM steps
and a continuous representation of the data
'''
prev_lik = - 1E16
best_lik = -1E16
best_sil = -1
new_sil = -1
tol = 0.01
patience = 0
is_looking_for_better_arch = False
# Initialize the parameters
eta = deepcopy(init['eta'])
psi = deepcopy(init['psi'])
lambda_bin = deepcopy(init['lambda_bin'])
lambda_ord = deepcopy(init['lambda_ord'])
lambda_cont = deepcopy(init['lambda_cont'])
lambda_categ = deepcopy(init['lambda_categ'])
H = deepcopy(init['H'])
w_s = deepcopy(init['w_s']) # Probability of path s' through the network for all s' in Omega
numobs = len(y)
likelihood = []
silhouette = []
it_num = 0
ratio = 1000
np.random.seed = seed
out = {} # Store the full output
# Dispatch variables between categories
y_bin = y[:, np.logical_or(var_distrib == 'bernoulli',var_distrib == 'binomial')]
nj_bin = nj[np.logical_or(var_distrib == 'bernoulli',var_distrib == 'binomial')].astype(int)
nb_bin = len(nj_bin)
y_ord = y[:, var_distrib == 'ordinal']
nj_ord = nj[var_distrib == 'ordinal'].astype(int)
nb_ord = len(nj_ord)
y_categ = y[:, var_distrib == 'categorical']
nj_categ = nj[var_distrib == 'categorical'].astype(int)
nb_categ = len(nj_categ)
y_cont = y[:, var_distrib == 'continuous'].astype(float)
nb_cont = y_cont.shape[1]
# Set y_count standard error to 1
y_cont = y_cont / y_cont.std(axis = 0, keepdims = True)
L = len(k)
k_aug = k + [1]
S = np.array([np.prod(k_aug[l:]) for l in range(L + 1)])
M = M_growth(1, r, numobs)
assert nb_bin + nb_ord + nb_cont + nb_categ > 0
if nb_bin + nb_ord + nb_cont + nb_categ != len(var_distrib):
raise ValueError('Some variable types were not understood,\
existing types are: continuous, categorical,\
ordinal, binomial and bernoulli')
# Compute the Gower matrix
if len(dm) == 0:
cat_features = np.logical_or(var_distrib == 'categorical', var_distrib == 'bernoulli')
dm = gower_matrix(y, cat_features = cat_features)
# Do not stop the iterations if there are some iterations left or if the likelihood is increasing
# or if we have not reached the maximum patience and if a new architecture was looked for
# in the previous iteration
while ((it_num < it) & (ratio > eps) & (patience <= max_patience)) | is_looking_for_better_arch:
print(it_num)
# The clustering layer is the one used to perform the clustering
# i.e. the layer l such that k[l] == n_clusters
if not(isnumeric(n_clusters)):
if n_clusters == 'auto':
clustering_layer = 0
else:
raise ValueError('Please enter an int or "auto" for n_clusters')
else:
assert (np.array(k) == n_clusters).any()
clustering_layer = np.argmax(np.array(k) == n_clusters)
#####################################################################################
################################# S step ############################################
#####################################################################################
#=====================================================================
# Draw from f(z^{l} | s, Theta) for all s in Omega
#=====================================================================
mu_s, sigma_s = compute_path_params(eta, H, psi)
sigma_s = ensure_psd(sigma_s)
z_s, zc_s = draw_z_s(mu_s, sigma_s, eta, M)
#========================================================================
# Draw from f(z^{l+1} | z^{l}, s, Theta) for l >= 1
#========================================================================
chsi = compute_chsi(H, psi, mu_s, sigma_s)
chsi = ensure_psd(chsi)
rho = compute_rho(eta, H, psi, mu_s, sigma_s, zc_s, chsi)
# In the following z2 and z1 will denote z^{l+1} and z^{l} respectively
z2_z1s = draw_z2_z1s(chsi, rho, M, r)
#=======================================================================
# Compute the p(y| z1) for all variable categories
#=======================================================================
py_zl1 = fy_zl1(lambda_bin, y_bin, nj_bin, lambda_ord, y_ord, nj_ord, \
lambda_categ, y_categ, nj_categ, y_cont, lambda_cont, z_s[0])
#========================================================================
# Draw from p(z1 | y, s) proportional to p(y | z1) * p(z1 | s) for all s
#========================================================================
zl1_ys = draw_zl1_ys(z_s, py_zl1, M)
#####################################################################################
################################# E step ############################################
#####################################################################################
#=====================================================================
# Compute conditional probabilities used in the appendix of asta paper
#=====================================================================
pzl1_ys, ps_y, p_y = E_step_GLLVM(z_s[0], mu_s[0], sigma_s[0], w_s, py_zl1)
#=====================================================================
# Compute p(z^{(l)}| s, y). Equation (5) of the paper
#=====================================================================
pz2_z1s = fz2_z1s(t(pzl1_ys, (1, 0, 2)), z2_z1s, chsi, rho, S)
pz_ys = fz_ys(t(pzl1_ys, (1, 0, 2)), pz2_z1s)
#=====================================================================
# Compute MFA expectations
#=====================================================================
Ez_ys, E_z1z2T_ys, E_z2z2T_ys, EeeT_ys = \
E_step_DGMM(zl1_ys, H, z_s, zc_s, z2_z1s, pz_ys, pz2_z1s, S)
###########################################################################
############################ M step #######################################
###########################################################################
#=======================================================
# Compute MFA Parameters
#=======================================================
w_s = np.mean(ps_y, axis = 0)
eta, H, psi = M_step_DGMM(Ez_ys, E_z1z2T_ys, E_z2z2T_ys, EeeT_ys, ps_y, H, k)
#=======================================================
# Identifiability conditions
#=======================================================
# Update eta, H and Psi values
H = diagonal_cond(H, psi)
Ez, AT = compute_z_moments(w_s, eta, H, psi)
eta, H, psi = identifiable_estim_DGMM(eta, H, psi, Ez, AT)
del(Ez)
#=======================================================
# Compute GLLVM Parameters
#=======================================================
lambda_bin = bin_params_GLLVM(y_bin, nj_bin, lambda_bin, ps_y, pzl1_ys, z_s[0], AT[0],\
tol = tol, maxstep = maxstep)
lambda_ord = ord_params_GLLVM(y_ord, nj_ord, lambda_ord, ps_y, pzl1_ys, z_s[0], AT[0],\
tol = tol, maxstep = maxstep)
lambda_categ = categ_params_GLLVM(y_categ, nj_categ, lambda_categ, ps_y, pzl1_ys, z_s[0], AT[0],\
tol = tol, maxstep = maxstep)
lambda_cont = cont_params_GLLVM(y_cont, lambda_cont, ps_y, pzl1_ys, z_s[0], AT[0],\
tol = tol, maxstep = maxstep)
###########################################################################
################## Clustering parameters updating #########################
###########################################################################
new_lik = np.sum(np.log(p_y))
likelihood.append(new_lik)
silhouette.append(new_sil)
ratio = abs((new_lik - prev_lik)/prev_lik)
idx_to_sum = tuple(set(range(1, L + 1)) - set([clustering_layer + 1]))
psl_y = ps_y.reshape(numobs, *k, order = 'C').sum(idx_to_sum)
temp_class = np.argmax(psl_y, axis = 1)
try:
new_sil = silhouette_score(dm, temp_class, metric = 'precomputed')
except ValueError:
new_sil = -1
# Store the params according to the silhouette or likelihood
is_better = (best_sil < new_sil) if use_silhouette else (best_lik < new_lik)
if is_better:
z = (ps_y[..., n_axis] * Ez_ys[clustering_layer]).sum(1)
best_sil = deepcopy(new_sil)
classes = deepcopy(temp_class)
'''
plt.figure(figsize=(8,8))
plt.scatter(z[:, 0], z[:, 1], c = classes)
plt.show()
'''
# Store the output
out['classes'] = deepcopy(classes)
out['best_z'] = deepcopy(z_s[0])
out['Ez.y'] = z
out['best_k'] = deepcopy(k)
out['best_r'] = deepcopy(r)
out['best_w_s'] = deepcopy(w_s)
out['lambda_bin'] = deepcopy(lambda_bin)
out['lambda_ord'] = deepcopy(lambda_ord)
out['lambda_categ'] = deepcopy(lambda_categ)
out['lambda_cont'] = deepcopy(lambda_cont)
out['eta'] = deepcopy(eta)
out['mu'] = deepcopy(mu_s)
out['sigma'] = deepcopy(sigma_s)
out['psl_y'] = deepcopy(psl_y)
out['ps_y'] = deepcopy(ps_y)
# Refresh the classes only if they provide a better explanation of the data
if best_lik < new_lik:
best_lik = deepcopy(prev_lik)
if prev_lik < new_lik:
patience = 0
M = M_growth(it_num + 2, r, numobs)
else:
patience += 1
###########################################################################
######################## Parameter selection #############################
###########################################################################
min_nb_clusters = 2
if isnumeric(n_clusters): # To change when add multi mode
is_not_min_specif = not(np.all(np.array(k) == n_clusters) & np.array_equal(r, [2,1]))
else:
is_not_min_specif = not(np.all(np.array(k) == min_nb_clusters) & np.array_equal(r, [2,1]))
is_looking_for_better_arch = look_for_simpler_network(it_num) & perform_selec & is_not_min_specif
if is_looking_for_better_arch:
r_to_keep = r_select(y_bin, y_ord, y_categ, y_cont, zl1_ys, z2_z1s, w_s)
# If r_l == 0, delete the last l + 1: layers
new_L = np.sum([len(rl) != 0 for rl in r_to_keep]) - 1
k_to_keep = k_select(w_s, k, new_L, clustering_layer, not(isnumeric(n_clusters)))
is_L_unchanged = (L == new_L)
is_r_unchanged = np.all([len(r_to_keep[l]) == r[l] for l in range(new_L + 1)])
is_k_unchanged = np.all([len(k_to_keep[l]) == k[l] for l in range(new_L)])
is_selection = not(is_r_unchanged & is_k_unchanged & is_L_unchanged)
assert new_L > 0
if is_selection:
eta = [eta[l][k_to_keep[l]] for l in range(new_L)]
eta = [eta[l][:, r_to_keep[l]] for l in range(new_L)]
H = [H[l][k_to_keep[l]] for l in range(new_L)]
H = [H[l][:, r_to_keep[l]] for l in range(new_L)]
H = [H[l][:, :, r_to_keep[l + 1]] for l in range(new_L)]
psi = [psi[l][k_to_keep[l]] for l in range(new_L)]
psi = [psi[l][:, r_to_keep[l]] for l in range(new_L)]
psi = [psi[l][:, :, r_to_keep[l]] for l in range(new_L)]
if nb_bin > 0:
# Add the intercept:
bin_r_to_keep = np.concatenate([[0], np.array(r_to_keep[0]) + 1])
lambda_bin = lambda_bin[:, bin_r_to_keep]
if nb_ord > 0:
# Intercept coefficients handling is a little more complicated here
lambda_ord_intercept = [lambda_ord_j[:-r[0]] for lambda_ord_j in lambda_ord]
Lambda_ord_var = np.stack([lambda_ord_j[-r[0]:] for lambda_ord_j in lambda_ord])
Lambda_ord_var = Lambda_ord_var[:, r_to_keep[0]]
lambda_ord = [np.concatenate([lambda_ord_intercept[j], Lambda_ord_var[j]])\
for j in range(nb_ord)]
# To recheck
if nb_cont > 0:
# Add the intercept:
cont_r_to_keep = np.concatenate([[0], np.array(r_to_keep[0]) + 1])
lambda_cont = lambda_cont[:, cont_r_to_keep]
if nb_categ > 0:
lambda_categ_intercept = [lambda_categ[j][:, 0] for j in range(nb_categ)]
Lambda_categ_var = [lambda_categ_j[:,-r[0]:] for lambda_categ_j in lambda_categ]
Lambda_categ_var = [lambda_categ_j[:, r_to_keep[0]] for lambda_categ_j in lambda_categ]
lambda_categ = [np.hstack([lambda_categ_intercept[j][..., n_axis], Lambda_categ_var[j]])\
for j in range(nb_categ)]
w = w_s.reshape(*k, order = 'C')
new_k_idx_grid = np.ix_(*k_to_keep[:new_L])
# If layer deletion, sum the last components of the paths
if L > new_L:
deleted_dims = tuple(range(L)[new_L:])
w_s = w[new_k_idx_grid].sum(deleted_dims).flatten(order = 'C')
else:
w_s = w[new_k_idx_grid].flatten(order = 'C')
w_s /= w_s.sum()
# Refresh the classes: TO RECHECK
#idx_to_sum = tuple(set(range(1, L + 1)) - set([clustering_layer + 1]))
#ps_y_tmp = ps_y.reshape(numobs, *k, order = 'C').sum(idx_to_sum)
#np.argmax(ps_y_tmp[:, k_to_keep[0]], axis = 1)
k = [len(k_to_keep[l]) for l in range(new_L)]
r = [len(r_to_keep[l]) for l in range(new_L + 1)]
k_aug = k + [1]
S = np.array([np.prod(k_aug[l:]) for l in range(new_L + 1)])
L = new_L
patience = 0
# Identifiability conditions
H = diagonal_cond(H, psi)
Ez, AT = compute_z_moments(w_s, eta, H, psi)
eta, H, psi = identifiable_estim_DGMM(eta, H, psi, Ez, AT)
del(Ez)
print('New architecture:')
print('k', k)
print('r', r)
print('L', L)
print('S',S)
print("w_s", len(w_s))
prev_lik = deepcopy(new_lik)
it_num = it_num + 1
print(likelihood)
print(silhouette)
out['likelihood'] = likelihood
out['silhouette'] = silhouette
return(out)
def dummies_gower(df):
return pd.DataFrame(gower_matrix(df.applymap(str), cat_features = [True for v in df.columns])).set_index(videos_df.index)
metrics.adjusted_mutual_info_score,
]
for artist_gt in range(ARTIST_GT):
data = pd.read_csv(
"../data preprocessing/final_df_with_encodings_with_price_binned.csv",
header=0,
usecols=[*features, *encodings])
filter_artist_gt(artist_gt)
n_rows = len(data)
mapping = {"(0, 250]": 0, "(250, 1250]": 1, "(1250, 4200]": 2}
labels_true = [mapping[x] for x in data['price_binned']]
results = []
for name, features_ in feature_groups.items():
result = [name]
features_used = gower.gower_matrix(data[features_])
cluster = SpectralClustering(NUMBER_OF_PRICE_BINS,
affinity='precomputed',
n_init=200,
n_jobs=-1).fit(features_used)
labels_pred = cluster.labels_
result += [m(labels_true, labels_pred) for m in clustering_metrics]
results.append(result)
print(
pd.DataFrame(
results, columns=[
"Feature", "V-measure", "Adj. Rand Index"
]).sort_values(by='Adj. Rand Index', ascending=False).to_latex(
f"../data preprocessing/artist_gt_{artist_gt}_ari.tex",
index=False,
caption=f"Number of rows {n_rows}"))
#y = y.where(~nan_mask, np.nan)
nj, nj_bin, nj_ord, nj_categ = compute_nj(full_contra, var_distrib)
nb_cont = np.sum(var_distrib == 'continuous')
p_new = full_contra.shape[1]
# Feature category (cf)
dtype = {full_contra.columns[j]: dtypes_dict[var_distrib[j]] for j in range(p_new)}
full_contra = full_contra.astype(dtype, copy=True)
# Feature category (cf)
cat_features = var_distrib == 'categorical'
# Defining distance matrix
dm3 = gower_matrix(full_contra, cat_features = cat_features)
#===========================================#
# Hyperparameters
#===========================================#
n_clusters = 2
nb_pobs = 100 # Target for pseudo observations
r = np.array([2, 1])
numobs = len(full_contra)
k = [n_clusters]
seed = 1
init_seed = 2
eps = 1E-05
nj, nj_bin, nj_ord, nj_categ = compute_nj(y, var_distrib)
y_np = y.values
nb_cont = np.sum(var_distrib == 'continuous')
p_new = y.shape[1]
# Feature category (cf)
cf_non_enc = np.logical_or(vd_categ_non_enc == 'categorical',
vd_categ_non_enc == 'bernoulli')
# Non encoded version of the dataset:
y_nenc_typed = y_categ_non_enc.astype(np.object)
y_np_nenc = y_nenc_typed.values
# Defining distances over the non encoded features
dm = gower_matrix(y_nenc_typed, cat_features=cf_non_enc)
dtype = {y.columns[j]: np.float64 if (var_distrib[j] != 'bernoulli') and \
(var_distrib[j] != 'categorical') else np.str for j in range(p_new)}
y = y.astype(dtype, copy=True)
#===========================================#
# Running the algorithm
#===========================================#
r = np.array([2, 1])
numobs = len(y)
k = [n_clusters]
seed = 1
s1 = '1'
s2 = '1000'
n1 = 1
n2 = 1000
types = {
'numbers': [n1, n2, 2, 2000],
'strings': [s1, s2, '2', '2000'],
'mixed': [n1, n2, s1, s2]
}
orders = {
'same': lambda a: [a, a],
'25%': lambda a: [a, [a[0], a[1], a[2], a[2]]],
'25% 2': lambda a: [a, [a[0], a[0], a[2], a[3]]],
'50%': lambda a: [a, [a[0], a[1], a[0], a[1]]],
'50% 2': lambda a: [a, [a[0], a[2], a[1], a[3]]],
'50% 3': lambda a: [a, [a[3], a[1], a[2], a[0]]],
'75%': lambda a: [a, [a[0], a[0], a[0], a[0]]],
'75% 2': lambda a: [a, [a[1], a[0], a[3], a[3]]],
'100%': lambda a: [a, [a[3], a[2], a[1], a[0]]]
}
for k, a in types.items():
print(k)
for o, func in orders.items():
print(o)
b = func(a)
X = pd.DataFrame(b)
X['c'] = 'c'
print(X)
print(gower.gower_matrix(X))
#print(set(discrete_k))
#test[col] = pd.cut(test[col], bins).map(lambda x: x.mid).astype(float)
le.fit(test[col].append(train[col]))
train[col] = le.transform(train[col])
k_dict[col] = deepcopy(le)
nj, nj_bin, nj_ord, nj_categ = compute_nj(train, var_distrib)
nb_cont = np.sum(var_distrib == 'continuous')
p_new = train.shape[1]
train_np = train.values
# Defining distances over the features
cat_features = pd.Series(var_distrib).isin(
['categorical', 'bernoulli']).to_list()
dm = gower_matrix(train.astype(np.object), cat_features=cat_features)
dtype = {train.columns[j]: np.float64 if (var_distrib[j] != 'bernoulli') and \
(var_distrib[j] != 'categorical') else np.str for j in range(p_new)}
train = train.astype(dtype, copy=True)
numobs = len(train)
#*****************************************************************
# Run MIAMI
#*****************************************************************
prince_init = dim_reduce_init(train, 2, k, r, nj, var_distrib, seed = None,\
use_famd=True)
out = MIAMI(train_np, 'auto', r, k, prince_init, var_distrib, nj, authorized_ranges, nb_pobs, it,\
eps, maxstep, seed, perform_selec = False, dm = dm, max_patience = 0)