def test_get_partial_table_y_labels():
delay = 0
data = ML_prepare(delay)
t1 = data.get_partial_table(x_section="all", y_labels=True)
assert t1["y"].columns.to_list() == ["SV_label", "SVI_label"]
t2 = data.get_partial_table(x_section="all", y_labels=False)
assert t2["y"].columns.to_list() == ["Settling_velocity", "SVI"]
def confusion_matrix_SVC(label: str, section: str, delay: int):
data = ML_prepare(delay)
table_xy = data.get_partial_table(x_section=section, y_labels=True)
X = table_xy.loc[:, 'x']
y = table_xy['y', label]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.25,
random_state=42)
clf = make_pipeline(StandardScaler(),
LinearSVC(random_state=0, tol=1e-5, max_iter=100000))
y_pred = clf.fit(X_train, y_train).predict(X_test)
le = preprocessing.LabelEncoder()
le.fit(list(y_pred))
y_pred = le.transform(y_pred)
y_test = le.transform(np.array(y_test))
cnf_matrix = confusion_matrix(y_test, y_pred)
plt.figure()
np.set_printoptions(precision=2)
plot_confusion_matrix(cnf_matrix,
classes=le.classes_,
normalize=False,
title='Confusion matrix, without normalization')
plt.savefig(
f"figures/SVC/LinearSVC_Confusion matrix, without normalization.png",
bbox_inches="tight")
def test_get_partial_table_wrong_input():
delay = 10
data = ML_prepare(delay)
section = "blah"
with pytest.raises(AssertionError):
t = data.get_partial_table(x_section=section, y_labels=True)
def test_get_partial_table_x_sections_lengths():
delay = 6
data = ML_prepare(delay)
sections = {"all": 27, "total_counts": 9, "filaments": 9, "various": 18}
for section in sections:
t = data.get_partial_table(x_section=section)
assert t["x"].shape[1] == sections[section]
def test_get_partial_table_no_nans():
delay = 10
data = ML_prepare(delay)
sections = ["all", "total_counts", "filaments", "various"]
for section in sections:
t = data.get_partial_table(x_section=section)
assert not t.isnull().values.any()
def test_regr_model_func():
data = ML_prepare(1)
table_xy = data.get_partial_table(x_section="various", y_labels=False)
X, y = table_xy.loc[:, "x"], table_xy.loc[:, "y"]
models_dict = create_models_dict()
regr_model = list(models_dict.keys())[0]
score, fitted_model = regr_model_func(X, y, regr_model)
assert isinstance(score, float)
module = getattr(fitted_model, "__module__", None)
assert "sklearn" in module
def choose_k_value(section: str, label: str, delay: int):
"""
plot graph of scores_k by k_range for KNeighbors model.
The user need to choose the k value by the result.
Parameters
----------
section : str
microorganisms section - should be: all or total_counts or filaments or various
label : str
label - should be: SV_label or SVI_label
delay : int
delay between the microscopic test which took place and the SVI test
return
----------
k : int
k choosen by the user
"""
if section not in {'all', 'total_counts', 'filaments', 'various'}:
raise ValueError(
"Please supply a valid section value: 'all','total_counts', 'filaments', 'various' "
)
if label not in {'SV_label', 'SVI_label'}:
raise ValueError(
"Please supply a valid label value: 'SV_label', 'SVI_label' ")
data = ML_prepare(delay)
table_xy = data.get_partial_table(x_section=section, y_labels=True)
X = table_xy.loc[:, 'x']
y = table_xy['y', label]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.25,
random_state=42)
scores_data = check_K_values(20, X_train, y_train, X_test, y_test)
sns.set()
sns.stripplot(data=scores_data, x='k', y='score', size=10)
plt.ylim(0, 1)
print(
"please look at the graph and choose k value. press enter to continue")
input()
plt.show()
print("please insert k value")
k = int(input())
return k
def get_day3_filaments_svi_data():
'''
Generates the most promising data producing regression results:
filaments microscopic data, and svi results of 3 days later.
return
--------
filaments_x: pd.DataFrame
microscopic measurements of all filament organisms.
filaments_svi: pd.Series
matching svi results of 3 days later
'''
data = ML_prepare(delay=3)
filaments_table = data.get_partial_table(x_section="filaments",
y_labels=False)
filaments_x = filaments_table.loc[:, "x"]
filaments_svi = filaments_table.loc[:, ("y", "SVI")]
return filaments_x, filaments_svi
def create_score_list_Knn(labels: list, sections: list, delay_lst: list,
k: int) -> list:
"""
create KNeighbors score list of all the prediction by label type, section of microorganism and delay
Parameters
----------
labels : list
list of labels: SV and SVI
sections : list
list of microorganisms sections: all, total_counts, filaments and various
delay_lst : list
list of delays between the microscopic test which took place and the SVI test
K : int
k value for KNeighbors model
return
----------
score_delay : list
score list of score predictions for each combination of label, section and delay
"""
if k <= 0:
raise ValueError("Please supply k value > 0 ")
score_delay = []
for label in labels:
for section in sections:
for delay in delay_lst:
data = ML_prepare(delay)
table_xy = data.get_partial_table(x_section=section,
y_labels=True)
X = table_xy.loc[:, 'x']
y = table_xy['y', label]
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25, random_state=42)
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)
y_predict = (knn.predict(X_test))
score_label = score_by_label(y_test, y_predict)
score = knn.score(X_test, y_test)
score_label.append(score)
score_delay.append(score_label)
return score_delay
def create_score_list_SVC(labels: list, sections: list,
delay_lst: list) -> list:
"""
create LinearSVC score list of all the prediction by label type, section of microorganism and delay
Parameters
----------
labels : list
list of labels: SV and SVI
sections : list
list of microorganisms section: all, total_counts, filaments and various
delay_lst : list
list of delays between the microscopic test which took place and the SVI test
return
----------
score_delay : list
score list of score predictions for each combination of label, section and delay
"""
score_delay = []
for label in labels:
for section in sections:
for delay in delay_lst:
data = ML_prepare(delay)
table_xy = data.get_partial_table(x_section=section,
y_labels=True)
X = table_xy.loc[:, 'x']
y = table_xy['y', label]
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25, random_state=42)
clf = make_pipeline(
StandardScaler(),
LinearSVC(random_state=0, tol=1e-5, max_iter=100000))
clf.fit(X_train, y_train)
y_predict = (clf.predict(X_test))
score_label = score_by_label(y_test, y_predict)
score = clf.score(X_test, y_test)
score_label.append(score)
score_delay.append(score_label)
# print(f"result for delay= {delay}, section= {section}, label={label} : score_bad={score_label[0]}, score_reasonable={score_label[1]}, score_good={score_label[2]}, score={score_label[3]}")
return score_delay
def create_section_and_PCA(data: ML_prepare, labled: bool = False):
"""
Creates PCA for every section (organism group) of the data:
"all", "filaments", "total_counts", "various".
Using helper function "pca_plot".
Plots by the "y", results, whether labeled or not.
Parameters
----------
data: ML_prepare
labled: bool
"""
section_lst = ["all", "filaments", "total_counts", "various"]
fig, ax = plt.subplots(4, 2)
for i in range(len(section_lst)):
table_xy = data.get_partial_table(x_section=section_lst[i],
y_labels=labled)
y_cols = table_xy.loc[:, "y"].columns.tolist()
for j in range(2):
### model on y = y_cols[j]
pca_plot(table_xy,
color_col=y_cols[j],
section=section_lst[i],
ax_i=ax[i, j])
fig.set_figheight(15)
fig.set_figwidth(15)
fig.suptitle(
f"PCA of groups, colored by output, delay = {data.delay} days",
fontsize=20,
y=1.02,
)
plt.tight_layout()
fig_name = "PCA_by_groups"
if labled:
fig_name = fig_name + "_labled"
plt.tight_layout()
fig.savefig("figures/" + fig_name + ".png", dpi=150, bbox_inches="tight")
plt.show()
def loop_over_sections_and_y(data: ML_prepare, regr_model):
'''
Generates for a given model, for a given delayed data,
scores of all 8 combinations:
"all_sv",
"all_svi",
"filaments_sv",
"filaments_svi",
"total_counts_sv",
"total_counts_svi",
"various_sv",
"various_svi"
Saves results in namedtuple.
Parameters
---------
data: ML_prepare
allready generated with chosen delay
regr_model: sklearn model object
return
---------
tup_scores: namedtuple,
'''
scores_lst = []
section_lst = ["all", "filaments", "total_counts", "various"]
for i in range(len(section_lst)):
table_xy = data.get_partial_table(x_section=section_lst[i],
y_labels=False)
y_cols = table_xy.loc[:, "y"].columns.tolist()
for j in range(2):
X = table_xy.loc[:, "x"]
y = table_xy.loc[:, ("y", y_cols[j])]
score, _ = regr_model_func(X, y, regr_model)
scores_lst.append(score)
tup_scores = insert_scores_to_namedtuple(scores_lst)
return tup_scores