From 12f760dce6bf49eca30db8be3ee78f3675e694c0 Mon Sep 17 00:00:00 2001
From: Nelly Barret <nelly.barret@etu.univ-lyon1.fr>
Date: Fri, 29 May 2020 17:29:25 +0200
Subject: [PATCH] [M] prediction with kmeans
---
predihood/classes/MethodPrediction.py | 3 +-
.../.~lock.data_density_filtered.csv# | 1 +
predihood/main.py | 4 +-
predihood/predict.py | 56 ++++++++++---------
4 files changed, 35 insertions(+), 29 deletions(-)
create mode 100644 predihood/generated_files/datasets/.~lock.data_density_filtered.csv#
diff --git a/predihood/classes/MethodPrediction.py b/predihood/classes/MethodPrediction.py
index b2f85172..ca7f6fda 100644
--- a/predihood/classes/MethodPrediction.py
+++ b/predihood/classes/MethodPrediction.py
@@ -36,7 +36,7 @@ class MethodPrediction(Method):
def predict(self, iris_code=None):
"""
- Predict environment variables for the given iris.
+ Predict environment variables for the given iris. The environment variable to predict is stored in the dataset as "env" variable
"""
iris_object = model.get_iris_from_code(iris_code)
iris_area = area(model.get_coords_from_code(iris_code)) / 1000000
@@ -69,6 +69,7 @@ class MethodPrediction(Method):
df = pd.DataFrame([iris_indicators_values], columns=iris_indicators_names)
self.prediction = self.classifier.predict(df)[0]
+ print(self.prediction)
def plot(self):
max_depths = np.linspace(1, 32, 32, endpoint=True)
diff --git a/predihood/generated_files/datasets/.~lock.data_density_filtered.csv# b/predihood/generated_files/datasets/.~lock.data_density_filtered.csv#
new file mode 100644
index 00000000..83abca58
--- /dev/null
+++ b/predihood/generated_files/datasets/.~lock.data_density_filtered.csv#
@@ -0,0 +1 @@
+,nelly,MacBook-Pro.local,29.05.2020 17:18,file:///Users/nelly/Library/Application%20Support/LibreOffice/4;
\ No newline at end of file
diff --git a/predihood/main.py b/predihood/main.py
index 19e55c36..ef28479b 100644
--- a/predihood/main.py
+++ b/predihood/main.py
@@ -96,10 +96,12 @@ def run_algorithm():
@app.route('/predict_iris', methods=["GET"])
def predict_iris():
iris_code_to_predict = request.args['iris_code']
+ # clf_name = request.args['clf']
+ # clf = get_classifier(clf_name)
data = Data(normalize="density", filter=True)
data.init_all_in_one()
- predictions = predict_one_iris(iris_code_to_predict, data, KNeighborsClassifier(n_neighbors=30), 0.8, 0.2, False)
+ predictions = predict_one_iris(iris_code_to_predict, data, KNeighborsClassifier(n_neighbors=30), 0.8, 0.2, False) # clf
return {"predictions": predictions}
diff --git a/predihood/predict.py b/predihood/predict.py
index 38dcbd92..fb53068d 100644
--- a/predihood/predict.py
+++ b/predihood/predict.py
@@ -426,9 +426,9 @@ def predict_one_iris(iris_code, data, clf, train_size, test_size, remove_outlier
for j, env in enumerate(ENVIRONMENT_VARIABLES):
predictions_lst = []
for top_k, lst in lists.items():
- dataset = Dataset(data, env, selected_indicators=lst[env], train_size=train_size, test_size=test_size, outliers=remove_outliers)
+ dataset = Dataset(data, env, selected_indicators=lst[env], train_size=train_size, test_size=test_size, outliers=remove_outliers, _type='supervised')
dataset.init_all_in_one()
- algo = MethodPrediction(name='', dataset=dataset, classifier=clf, _type='supervised')
+ algo = MethodPrediction(name='', dataset=dataset, classifier=clf)
# logging.debug("size of X_train: %d", len(algo2.dataset.X_train.columns))
# logging.debug(algo2.dataset.X_train.columns)
algo.fit()
@@ -438,7 +438,7 @@ def predict_one_iris(iris_code, data, clf, train_size, test_size, remove_outlier
return predictions
-def predict_k_means(data):
+def predict_k_means(data, iris_code):
nb_clusters = {
"batiment": 5,
"usage": 3,
@@ -447,30 +447,32 @@ def predict_k_means(data):
"geo": 9,
"social": 5
}
+
lists = get_selected_indicators_lists()
for j, env in enumerate(ENVIRONMENT_VARIABLES):
- # for top_k, lst in lists.items():
- # if top_k == "10":
- # dataset = Dataset(data, env, selected_indicators=lst[env], _type='unsupervised')
- # dataset.init_all_in_one()
- # cost = []
- # for i in range(1, 11):
- # kmeans = MethodPrediction(name='', dataset=dataset, classifier=KMeans(n_clusters=i, random_state=RANDOM_STATE))
- # kmeans.fit()
- # cost.append(kmeans.classifier.inertia_)
- # plt.plot(range(1, 11), cost, color='g', linewidth='3')
- # plt.xlabel("Value of K")
- # plt.ylabel("Squared Error (Cost)")
- # plt.show()
- # print("top-k:", top_k, "--", env)
- dataset = Dataset(data, env, _type='unsupervised') # selected_indicators=lst[env],
- dataset.init_all_in_one()
- # print("K-means with", nb_clusters[env], "clusters")
- # kmeans = MethodPrediction(name='', dataset=dataset, classifier=KMeans(n_clusters=nb_clusters[env], random_state=RANDOM_STATE))
- # kmeans.fit()
- # print(kmeans.classifier.labels_)
- chart = Chart(dataset=dataset, name='')
- chart.compute_trendline()
+ for top_k, lst in lists.items():
+ if top_k == "10":
+ dataset = Dataset(data, env, selected_indicators=lst[env], _type='unsupervised')
+ dataset.init_all_in_one()
+ # cost = []
+ # for i in range(1, 11):
+ # kmeans = MethodPrediction(name='', dataset=dataset, classifier=KMeans(n_clusters=i, random_state=RANDOM_STATE))
+ # kmeans.fit()
+ # cost.append(kmeans.classifier.inertia_)
+ # plt.plot(range(1, 11), cost, color='g', linewidth='3')
+ # plt.xlabel("Value of K")
+ # plt.ylabel("Squared Error (Cost)")
+ # plt.show()
+ # print("top-k:", top_k, "--", env)
+ # dataset = Dataset(data, env, _type='unsupervised') # selected_indicators=lst[env],
+ # dataset.init_all_in_one()
+ # print("K-means with", nb_clusters[env], "clusters")
+ kmeans = MethodPrediction(name='', dataset=dataset, classifier=KMeans(n_clusters=nb_clusters[env], random_state=RANDOM_STATE))
+ kmeans.fit()
+ kmeans.predict(iris_code)
+ print(kmeans.classifier.labels_)
+ # chart = Chart(dataset=dataset, name='')
+ # chart.compute_trendline()
if __name__ == '__main__':
@@ -494,7 +496,7 @@ if __name__ == '__main__':
#
data = Data(normalize="density", filter=True)
data.init_all_in_one()
- # predict_k_means(data)
+ predict_k_means(data, "692440102")
#
# data = Data(normalize="pop", filter=True)
# data.init_all_in_one()
@@ -504,4 +506,4 @@ if __name__ == '__main__':
# expe2(data)
# expe3(data)
# expe4(data, RandomForestClassifier(), 0.8, 0.2)
- expe5(data, RandomForestClassifier(), 0.8, 0.2)
+ # expe5(data, RandomForestClassifier(), 0.8, 0.2)
--
GitLab