"svm": "SVM",
"logistic_regression": "LG",
"linear_discriminant": "LD",
"kneighbors": "kNN",
"decision_tree": "DT",
"gaussian_nb": "GNB",
"random_forest": "RF",
"gradient_boosting": "GB",
"neural_network": "NN",
"knn": "kNN",
"Svm": "SVM",
"random": "Random",
"default": "Default"
}
db = DBHelper()
metadata = pd.DataFrame(db.get_all_metadata(), columns = db.metadata_columns()).drop("id", axis = 1)
models = pd.DataFrame(db.get_all_models(), columns = db.models_columns()).drop("id", axis = 1)
combinations = pd.DataFrame(db.get_all_combinations(), columns = db.combinations_columns())
preperformance = pd.DataFrame(db.get_all_preperformance(), columns = db.preperformance_columns()).drop("id", axis = 1)
# Not null preperformance
preperformance = preperformance[~preperformance.isnull().any(axis = 1)]
preperformance = pd.merge(preperformance, combinations, left_on = "combination_id", right_on = "id").drop(["combination_id", "id", "num_preprocesses"], axis = 1)
models = models.rename(columns = {"model": "classifier"})
models["preprocesses"] = "None"
scores = pd.concat([models, preperformance], sort = False)
scores = scores[scores.classifier != "neural_network"]
models = models[models.classifier != "neural_network"]
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import plotly.io as pio
import plotly.express as px
import plotly.graph_objects as go
import plotly.figure_factory as ff
import constants
from meta_db.db.DBHelper import DBHelper
db = DBHelper()
regressors = pd.DataFrame(db.get_all_regressors_preperformance(),
columns=[
"name", "score", "max_error",
"mean_absolute_error", "mean_squared_error",
"r2_score", "median_absolute_error",
"classifier", "preprocesses"
])
regressors_nopp = pd.DataFrame(db.get_all_regressors(),
columns=db.regressor_columns()).drop("id",
axis=1)
if not os.path.exists("analysis/plots"):
os.makedirs("analysis/plots")
if not os.path.exists("analysis/plots/meta_preperformance"):
os.makedirs("analysis/plots/meta_preperformance")
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import plotly.io as pio
import plotly.express as px
import plotly.graph_objects as go
import plotly.figure_factory as ff
import constants
from meta_db.db.DBHelper import DBHelper
db = DBHelper()
regressors = pd.DataFrame(db.get_all_regressors_preperformance(), columns = ["name", "score", "max_error", "mean_absolute_error", "mean_squared_error", "r2_score", "median_absolute_error", "classifier", "preprocesses"] )
regressors_nopp = pd.DataFrame(db.get_all_regressors(), columns = db.regressor_columns()).drop("id", axis = 1)
if not os.path.exists("analysis/plots"):
os.makedirs("analysis/plots")
if not os.path.exists("analysis/plots/meta_preperformance"):
os.makedirs("analysis/plots/meta_preperformance")
translator = {
"svm": "SVM",
"logistic_regression": "LG",
"linear_discriminant": "LD",
"kneighbors": "kNN",
"decision_tree": "DT",
"gaussian_nb": "GNB",
"random_forest": "RF",
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import constants
from meta_db.db.DBHelper import DBHelper
db = DBHelper()
models = pd.DataFrame(db.get_all_models(),
columns=db.models_columns()).drop("id", axis=1)
if not os.path.exists("analysis/plots"):
os.makedirs("analysis/plots")
if not os.path.exists("analysis/plots/meta_base"):
os.makedirs("analysis/plots/meta_base")
def box_plot(score="f1_macro_mean"):
data = []
for model in constants.CLASSIFIERS:
data.append(models[models.model == model][score])
fig = plt.figure(figsize=(12, 4))
ax = fig.add_subplot(111)
ax.boxplot(data,
showmeans=True,
meanline=True,
labels=[
name.replace("_", " ").capitalize()
for name in constants.CLASSIFIERS
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import constants
from meta_db.db.DBHelper import DBHelper
db = DBHelper()
combinations = pd.DataFrame(db.get_all_combinations(),
columns=db.combinations_columns())
preperformance = pd.DataFrame(db.get_all_preperformance(),
columns=db.preperformance_columns()).drop("id",
axis=1)
if not os.path.exists("analysis/plots"):
os.makedirs("analysis/plots")
if not os.path.exists("analysis/plots/preperformance"):
os.makedirs("analysis/plots/preperformance")
def box_plot(score="accuracy_mean", preprocess="SMOTE"):
data = []
for model in constants.CLASSIFIERS:
combination_id = int(
combinations[combinations.preprocesses == preprocess][
combinations.classifier == model]["id"])
data.append(preperformance[preperformance.combination_id ==
combination_id][score].dropna())
# import pdb; pdb.set_trace()
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import constants
from meta_db.db.DBHelper import DBHelper
db = DBHelper()
regressors = pd.DataFrame(db.get_all_regressors(),
columns=db.regressor_columns()).drop("id", axis=1)
if not os.path.exists("analysis/plots"):
os.makedirs("analysis/plots")
if not os.path.exists("analysis/plots/meta_level"):
os.makedirs("analysis/plots/meta_level")
# def box_plot(score = "accuracy_mean"):
score = "accuracy"
regressor_score = "mean_squared_error"
fig = plt.figure(figsize=(24, 24))
fig.suptitle(score, fontsize=12, fontweight='bold')
for indx, clf in enumerate(constants.CLASSIFIERS):
data = []
ax = fig.add_subplot(len(constants.CLASSIFIERS), 1, indx + 1)
ax.set_title(clf)
clf_data = regressors.query("classifier == '{}' and score == '{}'".format(
clf, score))
for reg in constants.REGRESSORS:
reg_info = clf_data.query("name == '{}'".format(reg))[regressor_score]
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import constants
from meta_db.db.DBHelper import DBHelper
db = DBHelper()
regressors = pd.DataFrame(db.get_all_regressors_preperformance(),
columns=[
"name", "score", "max_error",
"mean_absolute_error", "mean_squared_error",
"r2_score", "median_absolute_error",
"classifier", "preprocesses"
])
if not os.path.exists("analysis/plots"):
os.makedirs("analysis/plots")
if not os.path.exists("analysis/plots/meta_preperformance"):
os.makedirs("analysis/plots/meta_preperformance")
def box_plot(preprocess):
score = "accuracy"
regressor_score = "mean_squared_error"
fig = plt.figure(figsize=(24, 24))
fig.suptitle(score, fontsize=12, fontweight='bold')
for indx, clf in enumerate(constants.CLASSIFIERS):
data = []
