'ch.uzh.ciclassifier.features.travisci.BuildTimeAverage',
'ch.uzh.ciclassifier.features.travisci.BuildSuccessRatio',
'ch.uzh.ciclassifier.features.travisci.BuildTimeLatestAverage',
'ch.uzh.ciclassifier.features.travisci.ManualInteractionRatio',
'ch.uzh.ciclassifier.features.travisci.PullRequestRatio',
'ch.uzh.ciclassifier.features.travisci.TimeToFixAverage',
'ch.uzh.ciclassifier.features.travisci.TimeToFixLatestAverage',
]
FEATURES_FILE = 'data/truth.csv'
TYPES = ['configuration', 'repository', 'travisci']
results = []
for i in range(len(TYPES)):
for permutation in list(itertools.combinations(TYPES, i + 1)):
raw_data = pd.read_csv(FEATURES_FILE)
features = raw_data[get_features()]
for feature in AVAILABLE_FEATURES:
featureType = helper.type_from_feature_name(feature)
if featureType not in permutation and feature in features:
features = features.drop(feature, axis=1)
labels = np.array(raw_data['actual'])
features = np.array(features)
cv = RepeatedKFold(n_splits=10, n_repeats=10, random_state=42)
rf = RandomForestClassifier(**get_rf_parameters())
scores = cross_val_score(rf,
features,
labels,
scoring='accuracy',
import csv
import pickle
import pandas as pd
from parameters import get_features
TARGET = 'results/ciclassifier_raw_new.csv'
EXPORT = 'results/ciclassifier_new.csv'
MODEL_PATH = '../models/classifier_configuration.sav'
raw_data = pd.read_csv(TARGET)
to_predict = raw_data.drop('project', axis=1)
features = get_features()
features = list(filter(lambda f: "configuration" in f, features))
to_predict = to_predict[features]
model = pickle.load(open(MODEL_PATH, 'rb'))
predictions = model.predict(to_predict)
projects = raw_data.to_dict('records')
with open(EXPORT, 'w', newline='') as csvfile:
fieldnames = ['project']
fieldnames.extend(features)
fieldnames.append('score')
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
index = 0
for project in projects:
prediction = predictions[index]
project['score'] = prediction
from scipy.stats import stats
from helper import short_name
from parameters import get_features, beautify_feature_name
DATA = '../data/truth.csv'
raw_data = pd.read_csv(DATA)
good = raw_data.loc[raw_data['actual'] == 1]
bad = raw_data.loc[raw_data['actual'] == 0]
fig, axs = plt.subplots(6, 4, figsize=(10, 12))
index = 0
row = 0
for feature in get_features():
beautiful_name = beautify_feature_name(feature)
col = index % 4
print(row, col)
tmp_good = good[feature]
#tmp_good = tmp_good[tmp_good.between(tmp_good.quantile(.00), tmp_good.quantile(.95))]
# tmp_good = tmp_good[(np.abs(stats.zscore(tmp_good)) < 3)]
tmp_bad = bad[feature]
# tmp_bad = tmp_bad[tmp_bad.between(tmp_bad.quantile(.00), tmp_bad.quantile(.95))]
# tmp_bad = tmp_bad[(np.abs(stats.zscore(tmp_bad)) < 3)]
#axs[row, col].hist([good[feature],bad[feature]], 20, alpha=0.5)
#axs[row, col].hist(, 20, facecolor='r', alpha=0.5)
'ch.uzh.ciclassifier.features.travisci.PullRequestRatio',
'ch.uzh.ciclassifier.features.travisci.TimeToFixAverage',
'ch.uzh.ciclassifier.features.travisci.TimeToFixLatestAverage',
]
FEATURES_FILE = 'data/truth.csv'
LANGAUGES = ['Ruby', 'JavaScript', 'Python', 'Java', 'C++', 'PHP']
results = []
NUMBER_OF_RUNS = 10
for language in LANGAUGES:
raw_data = pd.read_csv(FEATURES_FILE)
subset = raw_data.loc[raw_data['language'] == language]
features = subset[get_features()]
labels = np.array(subset['actual'])
features = np.array(features)
cv = RepeatedKFold(n_splits=10, n_repeats=10, random_state=42)
rf = RandomForestClassifier(**get_rf_parameters())
scores = cross_val_score(rf,
features,
labels,
scoring='accuracy',
cv=cv,
n_jobs=-1)
accuracies = []
precisions = []
recalls = []