def run(self):
self.df = pd.read_csv(self.inputDataPath)
wb = xlsxwriter.Workbook(self.outputDataPath)
fmtBold = wb.add_format({'bold': True})
wsSummary = wb.add_worksheet("Summary")
wsData = wb.add_worksheet("Data")
wsChart = wb.add_worksheet("Chart")
wsSummary.set_column("A:I", 18)
wsData.set_column("A:I", 18)
columns = sorted(self.df.columns)
columns.insert(0, "K")
i = 0
for j in range(0, len(columns)):
wsData.write(i, j, columns[j], fmtBold)
i = 1
beginRow = i
for index, row in self.df.iterrows():
wsData.write(i, 0, i)
for j in range(1, len(columns)):
wsData.write(i, j, row[columns[j]])
j += 1
i += 1
endRow = i
chart = wb.add_chart({"type": "scatter"})
categories = "=Data!$A$2:$A101"
series1 = "=Data!$B$2:$B101"
series2 = "=Data!$C$2:$C101"
series3 = "=Data!$D$2:$D101"
chart.add_series({"categories": categories, "values": series1})
chart.add_series({"categories": categories, "values": series2})
chart.add_series({"categories": categories, "values": series3})
chart.set_x_axis({"Name": "KFold"})
chart.set_y_axis({"Name": "Score"})
wsChart.insert_chart("A1", chart)
columns.pop(0)
stats = ["Classifier", "Mean", "Median", "Std", "Var", "Min", "Max"]
for j in range(0, len(stats)):
wsSummary.write(0, j, stats[j], fmtBold)
for i in range(0, len(columns)):
classifier = columns[i]
sMean = Number.asFloat(np.mean(self.df[classifier]), 3)
sMedian = Number.asFloat(np.median(self.df[classifier]), 3)
sStd = Number.asFloat(np.std(self.df[classifier]), 3)
sVar = Number.asFloat(np.var(self.df[classifier]), 3)
sMin = np.min(self.df[classifier])
sMax = np.max(self.df[classifier])
stats = [classifier, sMean, sMedian, sStd, sVar, sMin, sMax]
for j in range(0, len(stats)):
if j == 0:
wsSummary.write(i + 1, j, stats[j], fmtBold)
else:
wsSummary.write(i + 1, j, stats[j])
wb.close()
Msg.raw(self.df)
def run(self):
self.initialize()
scoreKeeper = Data.buildDictByKeys(self.classifiers.keys(), [])
for i in range(0, self.cycles):
Msg.show("Cycle {0} of {1}".format(i + 1, self.cycles))
scores = self.build(self.inputDataPath)
for classifier in scores.keys():
scoreKeeper[classifier].extend(scores[classifier])
df = pd.DataFrame.from_dict(scoreKeeper)
Msg.raw(df)
df.to_csv(self.outputDataPath, index=False, float_format='%.2f')
Msg.show("Saved results -> {0}".format(self.outputDataPath))
def build(self, inputDataPath):
Msg.raw("Analyzing <-> {0}".format(inputDataPath))
self.ingestData(inputDataPath)
kf = KFold(n_splits=self.kFolds,
shuffle=self.randomizeDataFlag,
random_state=None)
X = self.dfFeatures.values
y = self.dfLabel.values.astype(dtype="int64")
scoreKeeper = {}
for name, classifier in sorted(list(self.classifiers.items())):
scores = cross_val_score(classifier, X, y, cv=kf)
if not name in scoreKeeper:
scoreKeeper[name] = []
scoreKeeper[name].extend(scores)
return scoreKeeper