def evaluate(self, array_datas):
"""
Create a scatter plot between multiple variables
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas)
if command_status == CommandStatus.Error:
return result_object
if len(df.columns) <= 1:
Printer.Print("There needs to be atleast two variables to perform multiscatter plot!")
return result_object
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
if StatContainer.ground_truth is None or len(StatContainer.ground_truth.data) != df.shape[0]:
df.dropna(inplace=True)
pd.plotting.scatter_matrix(df, alpha=0.2, diagonal='kde', ax=ax)
else:
gt1 = pd.Series(StatContainer.filterGroundTruth())
df, gt1 = DataGuru.removenan(df, gt1)
lut = dict(zip(gt1.unique(), np.linspace(0, 1, gt1.unique().size)))
row_colors = gt1.map(lut)
pd.plotting.scatter_matrix(df, alpha=0.2, diagonal='kde', c=row_colors, cmap="jet", ax=ax)
f.suptitle(cname)
win.show()
return VizContainer.createResult(win, array_datas, ['multiscatter'])
def evaluate(self, array_datas):
"""
Create a box plot between multiple variables
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(
array_datas)
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
if StatContainer.ground_truth is None or len(
StatContainer.ground_truth.data) != df.shape[0]:
df.dropna(inplace=True)
df.boxplot(ax=ax)
else:
ground_truth = StatContainer.ground_truth.name
df[ground_truth] = StatContainer.filterGroundTruth()
df.dropna(inplace=True)
df.boxplot(by=ground_truth, ax=ax)
f.suptitle("")
win.show()
return VizContainer.createResult(win, array_datas, ['box'])
def evaluate(self, data_frame, array_datas, classifier_algo, pre_evaluate_results=None):
"""
Train a classifier on multiple arrays
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
if type(pre_evaluate_results) is not list:
Printer.Print("Pre evaluation results failed! Attach bug report!")
return result_object
win = Window.window()
if data_frame is not None:
result_object = VizContainer.createResult(win, data_frame, ['cval'])
elif array_datas is not None:
result_object = VizContainer.createResult(win, array_datas, ['cval'])
else:
Printer.Print("Provide one of data frame or array datas")
return result_object
cv_output, aux_output = pre_evaluate_results
properties, model_data = aux_output.data
result_object.data = [win, properties, model_data, self.processkFoldCV]
self.printkValueMessage(cv_output.data[0])
self.updateWindow(win, cv_output.data[1], cv_output.data[2], model_data[1], properties["title"])
self.modify_figure.evaluate(result_object)
return result_object
def evaluate(self, array_datas):
"""
Create a line plot
"""
sns.set(color_codes=True)
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas, useCategorical=True, expand_single=True,
remove_nan=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
elif (df.shape[0] == 0 or
(df.shape[1] == 1 and
np.issubdtype(array_datas[0].data.dtype, np.number) == False)):
Printer.Print("No data left to plot after cleaning up!")
return ResultObject(None, None, None, CommandStatus.Error)
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
ax.set_title(cname)
df.plot(ax=ax)
win.show()
return VizContainer.createResult(win, array_datas, ['line'])
def evaluate(self, array_datas):
"""
Visualize the relationship between variables
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
df = pd.DataFrame()
for array_data in array_datas:
if (np.issubdtype(array_data.data.dtype, np.number)) == True:
Printer.Print("The data to plot is not categorical, Please use scatter plot")
return result_object
df[" ".join(array_data.keyword_list)] = array_data.data
df.dropna(inplace=True)
df = df.pivot_table(
index=df.columns[0], columns=df.columns[1], aggfunc=np.size, fill_value=0)
Printer.Print("Displaying heatmap")
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
sns.heatmap(df, ax=ax)
win.show()
return VizContainer.createResult(win, array_datas, ['heatmap'])
def evaluate(self, image):
"""
Display the image specified
"""
try:
if image.data_type is DataType.file_name:
file_path = image.data.path
if not os.path.isfile(file_path):
Printer.Print("Cannot find image file: ", file_path)
raise RuntimeError
curr_image = imread(file_path)
result_object = ResultObject(
curr_image, image.keyword_list, DataType.image, CommandStatus.Success)
else:
curr_image = image.data
result_object = ResultObject(
None, None, None, CommandStatus.Success)
image_name = image.keyword_list[0]
win = Window.window()
plt.imshow(curr_image)
plt.gca().axis('off')
win.show()
Printer.Print("Displaying image" + image_name)
except:
result_object = ResultObject(None, None, None, CommandStatus.Error)
return result_object
def evaluate(self, array_datas):
"""
Displaying a heatmap for data visualization
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(
array_datas, remove_nan=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
Printer.Print("Displaying heatmap")
win = Window.window()
f = win.gcf()
if StatContainer.ground_truth is None:
sns.clustermap(df,
cbar=True,
square=False,
annot=False,
cmap='jet',
standard_scale=1)
else:
gt1 = pd.Series(StatContainer.ground_truth.data)
lut = dict(zip(gt1.unique(), "rbg"))
row_colors = gt1.map(lut)
sns.clustermap(df,
standard_scale=1,
row_colors=row_colors,
cmap="jet")
win.show()
return VizContainer.createResult(win, array_datas, ['heatmap'])
def evaluate(self, array_datas):
"""
Create a violin plot for multiple variables
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas, remove_nan=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
if StatContainer.ground_truth is None or len(StatContainer.ground_truth.data) != df.shape[0]:
df.dropna(inplace=True)
sns.violinplot(data=df, ax=ax)
else:
ground_truth = " ".join(StatContainer.ground_truth.keyword_list)
df[ground_truth] = StatContainer.filterGroundTruth()
df.dropna(inplace=True)
df1 = pd.melt(df, id_vars=ground_truth)
sns.violinplot(data=df1, ax=ax, x='variable', y='value', hue=ground_truth)
win.show()
return VizContainer.createResult(win, array_datas, ['violin'])
def evaluate(self, data_frame, classifier_model):
"""
Run a trained classifier on multiple arrays
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
# Get the data frame
sns.set(color_codes=True)
#command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(array_datas)
df = data_frame.data
# if command_status == CommandStatus.Error:
# return ResultObject(None, None, None, CommandStatus.Error)
if StatContainer.ground_truth is None:
Printer.Print("Please set a feature vector to ground truth by",
"typing set ground truth to",
"to get the prediction accuracy")
result_object = ResultObject(None, None, None, CommandStatus.Error)
return result_object
else:
df = DataGuru.removeGT(df, StatContainer.ground_truth)
Y = StatContainer.ground_truth.data
# Remove nans:
df, Y = DataGuru.removenan(df, Y)
X = df.values
# Get the classifier model
trained_model = classifier_model.data
model = trained_model['Model']
scaler = trained_model['Scaler']
# Scale the values based on the training standardizer
X = scaler.transform(X)
# Code to run the classifier
# Plot the classification result
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
Printer.Print('Running the trained classifier...')
predictions = model.predict(X)
accuracy = metrics.accuracy_score(predictions, Y)
Printer.Print("Accuracy : %s" % "{0:.3%}".format(accuracy))
cm = metrics.confusion_matrix(Y, predictions)
DataGuru.plot_confusion_matrix(cm,
np.unique(Y),
ax,
title="confusion matrix")
win.show()
# TODO Need to save the result
result_object = ResultObject(None, None, None, CommandStatus.Success)
return result_object
def evaluate(self, data_frame, array_datas):
"""
Run Isomap on a dataset of multiple arrays
"""
# Get the data frame
if data_frame is not None:
df = data_frame.data
df = DataGuru.convertStrCols_toNumeric(df)
cname = data_frame.name
elif array_datas is not None:
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas, useCategorical=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
else:
Printer.Print("Please provide data frame or arrays to analyze")
return ResultObject(None, None, None, CommandStatus.Error)
Y = None
if StatContainer.ground_truth is not None:
df = DataGuru.removeGT(df, StatContainer.ground_truth)
Y = StatContainer.filterGroundTruth()
df, Y = DataGuru.removenan(df, Y)
# Remove nans:
else:
df.dropna(inplace=True)
# Get the Isomap model
# Code to run the classifier
X = df.values
# Get a standard scaler for the extracted data X
scaler = preprocessing.StandardScaler().fit(X)
X = scaler.transform(X)
# Train the classifier
win = Window.window()
properties = self.createDefaultProperties()
properties['title'] = cname
# return ResultObject(None, None, None, CommandStatus.Success)
if data_frame is not None:
result_object = VizContainer.createResult(win, data_frame,
['ismp'])
else:
result_object = VizContainer.createResult(win, array_datas,
['ismp'])
result_object.data = [win, properties, [X, Y], self.updateFigure]
self.updateFigure(result_object.data)
self.modify_figure.evaluate(result_object)
return result_object
def evaluate(self, array_data):
"""
Create a pie plot
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
stTitle = " ".join(array_data.keyword_list)
if StatContainer.conditional_array is not None and len(
StatContainer.conditional_array.data) == array_data.data.size:
inds = StatContainer.conditional_array.data
Printer.Print("Nfiltered: ", np.sum(inds))
else:
inds = np.full(array_data.data.size, True)
col_data = pd.Series(array_data.data[inds], name='array')
col_data.dropna(inplace=True)
try:
uniqVals, inv, counts = np.unique(col_data,
return_inverse=True,
return_counts=True)
except:
return ResultObject(None, None, None, CommandStatus.Error)
if len(uniqVals) > self.max_unique:
if isinstance(uniqVals[0], str):
best_idx = np.argpartition(counts,
-self.max_unique)[-self.max_unique:]
idx = np.isin(inv, best_idx)
col_data = col_data[idx]
elif np.issubdtype(col_data.dtype, np.number):
# Convert to categorical
col_data = pd.cut(col_data, 10)
uniqVals = True
else:
uniqVals = None
if uniqVals is not None:
counts = pd.Series(np.ones(col_data.size), name='count')
concat_df = pd.concat([counts, col_data], axis=1)
ds = concat_df.groupby(col_data.name).sum()['count']
else:
Printer.Print("Too many unique values to plot on a pie chart\n")
Printer.Print("Please select another chart type")
return result_object
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
ds.plot.pie(figsize=(8, 8), ax=ax)
ax.set_title(stTitle)
ax.set_xlabel('')
ax.set_aspect('equal')
win.show()
return VizContainer.createResult(win, array_data, ['pie'])
def evaluate(self, array_datas):
"""
Create a histogram for multiple variables
"""
sns.set(color_codes=True)
command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(
array_datas, useCategorical=True, remove_nan=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
dCol = df[df.columns[0]]
try:
uniqVals, inv, counts = np.unique(dCol,
return_inverse=True,
return_counts=True)
except:
return ResultObject(None, None, None, CommandStatus.Error)
if len(uniqVals) > self.max_unique:
if isinstance(uniqVals[0], str):
best_idx = np.argpartition(counts,
-self.max_unique)[-self.max_unique:]
idx = np.isin(inv, best_idx)
dCol = dCol[idx]
else:
uniqVals = None
if uniqVals is not None and isinstance(uniqVals[0], str):
max_len = max([len(uniqVal) for uniqVal in uniqVals])
else:
max_len = 0
if (uniqVals is None and not np.issubdtype(dCol.dtype, np.number)):
Printer.Print("Too many unique values in non-numeric type data")
return ResultObject(None, None, None, CommandStatus.Error)
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
# TODO Create an argument for setting number of bins
if uniqVals is not None:
if len(uniqVals) > 5 and max_len > 8:
df = dCol.to_frame(name=kl1[0])
sns.countplot(y=kl1[0], data=df, ax=ax)
else:
df = dCol.to_frame(name=kl1[0])
sns.countplot(x=kl1[0], data=df, ax=ax)
elif np.issubdtype(dCol.dtype, np.number):
df.plot.hist(stacked=True, ax=ax)
win.show()
return VizContainer.createResult(win, array_datas,
['histogram', 'hist'])
def read(self, file_path, keyword_list):
try:
data = imread(file_path)
except:
return ResultObject(None, None, None,
command_status=CommandStatus.Error)
win = Window.window()
#f = win.gcf()
plt.imshow(data)
plt.gca().axis('off')
win.show()
# Initialize image manipulation command group
result = ResultObject(data, keyword_list, DataType.image,
CommandStatus.Success, add_to_cache=True)
result.createName(keyword_list)
return result
def evaluate(self, array_datas):
"""
Create a scatter plot between two variables
"""
sns.set(color_codes=True)
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas)
if command_status == CommandStatus.Error:
Printer.Print("please try the following command:",
"Visualize comparison between...")
return ResultObject(None, None, None, CommandStatus.Error)
properties = self.createDefaultProperties()
properties['title'] = cname
win = Window.window()
row_colors = None
if StatContainer.ground_truth is None or len(StatContainer.ground_truth.data) != df.shape[0]:
df.dropna(inplace=True)
if df.shape[0] == 0:
return ResultObject(None, None, None, CommandStatus.Error)
array = df.values
else:
gt1 = pd.Series(StatContainer.filterGroundTruth())
df, gt1 = DataGuru.removenan(df, gt1)
if df.shape[0] == 0:
return ResultObject(None, None, None, CommandStatus.Error)
lut = dict(zip(gt1.unique(), np.linspace(0, 1, gt1.unique().size)))
row_colors = gt1.map(lut)
array = df.values
result_object = VizContainer.createResult(
win, array_datas, ['scatter2d'])
result_object.data = [win, properties, [
array, row_colors, kl1], self.updateFigure]
self.updateFigure(result_object.data)
self.modify_figure.evaluate(result_object)
return result_object
def evaluate(self, array_datas):
"""
Find the correlation between two or more variables
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
if len(array_datas) < 2:
Printer.Print("Need atleast two arrays to compute correlation")
return ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(
array_datas, remove_nan=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
corr_res = df.corr()
if len(array_datas) == 2:
Printer.Print("The correlation between ", kl1[0], " and ", kl1[1],
" is ", str(corr_res.values[0][1]))
Printer.Print("Displaying the result as a heatmap")
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
sns.heatmap(corr_res,
cbar=True,
square=True,
annot=True,
fmt='.2f',
annot_kws={'size': 15},
xticklabels=df.columns,
yticklabels=df.columns,
cmap='jet',
ax=ax)
win.show()
return VizContainer.createResult(win, array_datas, ['correlation'])
def evaluate(self, array_datas):
"""
Create a bar plot between multiple variables
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
sns.set(color_codes=True)
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
if StatContainer.ground_truth is None:
gtVals = np.ones(df.shape[0])
ground_truth = 'ground_truth'
else:
gtVals = StatContainer.filterGroundTruth()
ground_truth = StatContainer.ground_truth.name
if len(gtVals) != df.shape[0]:
print("ground truth does not match with df shape")
print(len(gtVals), df.shape[0])
gtVals = np.ones(df.shape[0])
ground_truth = 'ground_truth'
# Remove nans:
df[ground_truth] = gtVals
df.dropna(inplace=True)
gtVals = df[ground_truth]
uniqVals = StatContainer.isCategorical(gtVals)
binned_ground_truth = False
if uniqVals is None and np.issubdtype(gtVals.dtype, np.number):
# Convert to categorical
df[ground_truth] = pd.cut(gtVals, 10)
binned_ground_truth = True
if binned_ground_truth is True or uniqVals is not None:
gb = df.groupby(ground_truth)
df_mean = gb.mean()
df_errors = gb.std()
if uniqVals is not None and isinstance(uniqVals[0], str):
truncated_uniqVals, _ = StatContainer.removeCommonNames(
df_mean.index)
df_mean.index = truncated_uniqVals
df_errors.index = truncated_uniqVals
# Number of uniq_vals x number of arrs
df_mean_shape = df_mean.shape
if (not binned_ground_truth
and df_mean_shape[1] >= df_mean_shape[0]):
df_mean = df_mean.T
df_errors = df_errors.T
else:
Printer.Print("Ground truth could not be mapped to",
"categorical array\n")
Printer.Print("Please clear or select appropriate ground truth")
return result_object
properties = self.createDefaultProperties()
properties['title'] = cname
if uniqVals is not None and isinstance(uniqVals[0], str):
max_len = max([len(uniqVal) for uniqVal in uniqVals])
else:
max_len = 0
if (binned_ground_truth or
(uniqVals is not None and len(uniqVals) > 5 and max_len > 8)):
properties["horizontal"] = True
if binned_ground_truth:
properties["overwrite_labels"] = True
properties["ylabel"] = StatContainer.ground_truth.name
win = Window.window()
result_object = VizContainer.createResult(win, array_datas, ['bar'])
result_object.data = [
win, properties, [df_mean, df_errors], self.updateFigure
]
self.updateFigure(result_object.data)
self.modify_figure.evaluate(result_object)
return result_object
def evaluate(self, data_frame, classifier_algos):
"""
Train a classifier on multiple arrays
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
# Get the data frame
sns.set(color_codes=True)
df = data_frame.data
#command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(array_datas)
# if command_status == CommandStatus.Error:
# return ResultObject(None, None, None, CommandStatus.Error)
# Get the ground truth array
if StatContainer.ground_truth is None:
Printer.Print("Please set a feature vector to ground truth by",
"typing set ground truth before using this command")
result_object = ResultObject(None, None, None, CommandStatus.Error)
return result_object
else:
df = DataGuru.removeGT(df, StatContainer.ground_truth)
Y = StatContainer.ground_truth.data
# Remove nans:
df, Y = DataGuru.removenan(df, Y)
Printer.Print("Training classifier using the following features:")
Printer.Print(df.columns)
# Get all the classifier models to test against each other
modelList = []
Printer.Print("Testing the following classifiers: ")
for classifier_algo in classifier_algos:
model = (classifier_algo.data[0])
Printer.Print(classifier_algo.name)
modelList.append({'Name': classifier_algo.name, 'Model': model})
# Code to run the classifier
X = df.values
# Get a standard scaler for the extracted data X
scaler = preprocessing.StandardScaler().fit(X)
X = scaler.transform(X)
Printer.Print('Finding the best classifier using',
'k fold cross validation...')
all_cv_scores, all_mean_cv_scores, all_confusion_matrices = DataGuru.FindBestClassifier(X, Y, modelList, 10)
Printer.Print('\n\nPlotting the confusion matrices...\n')
for iter in range(len(modelList)):
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
DataGuru.plot_confusion_matrix(all_confusion_matrices[iter], np.unique(Y), ax, title=modelList[iter]['Name'])
win.show()
Printer.Print("\n\nBest classifier is " + modelList[np.argmax(all_mean_cv_scores)]['Name'] + " with an accuracy of - %.2f%% " % max(all_mean_cv_scores))
# TODO Need to save the model
# Ask user for a name for the model
result_object = ResultObject(None, None, None, CommandStatus.Success)
return result_object
def evaluate(self, data_frame, array_datas):
"""
Run pca on a dataset of multiple arrays
"""
# Get the data frame
if data_frame is not None:
df = data_frame.data
df = DataGuru.convertStrCols_toNumeric(df)
cname = data_frame.name
elif array_datas is not None:
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas, useCategorical=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
else:
Printer.Print("Please provide data frame or arrays to analyze")
return ResultObject(None, None, None, CommandStatus.Error)
Y = None
if StatContainer.ground_truth is not None:
df = DataGuru.removeGT(df, StatContainer.ground_truth)
Y = StatContainer.filterGroundTruth()
# Remove nans:
df, Y = DataGuru.removenan(df, Y)
else:
df.dropna(inplace=True)
# Code to run the classifier
X = df.values
# Get a standard scaler for the extracted data X
scaler = preprocessing.StandardScaler().fit(X)
X = scaler.transform(X)
# Train the classifier
pca = PCA(n_components=2)
pca_res = pca.fit_transform(X)
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
if Y is None:
sc = ax.scatter(pca_res[:, 0],
pca_res[:, 1],
cmap="jet",
edgecolor="None",
alpha=0.35)
else:
sc = ax.scatter(pca_res[:, 0],
pca_res[:, 1],
c=Y,
cmap="jet",
edgecolor="None",
alpha=0.35)
cbar = plt.colorbar(sc)
cbar.ax.get_yaxis().labelpad = 15
cbar.ax.set_ylabel(StatContainer.ground_truth.name, rotation=270)
ax.set_title(cname)
win.show()
# return ResultObject(None, None, None, CommandStatus.Success)
if data_frame is not None:
return VizContainer.createResult(win, data_frame, ['pca'])
else:
return VizContainer.createResult(win, array_datas, ['pca'])
def evaluate(self, data_frame, array_datas, target):
"""
Run clustering on a dataset of multiple arrays
"""
# Get the data frame
if data_frame is not None:
df = data_frame.data
cname = data_frame.name
elif array_datas is not None:
command_status, df, kl1, cname = DataGuru.transformArray_to_dataFrame(
array_datas, useCategorical=True)
if command_status == CommandStatus.Error:
return ResultObject(None, None, None, CommandStatus.Error)
else:
Printer.Print("Please provide data frame or arrays to analyze")
return ResultObject(None, None, None, CommandStatus.Error)
Y = None
if StatContainer.ground_truth is not None:
df = DataGuru.removeGT(df, StatContainer.ground_truth)
Y = StatContainer.filterGroundTruth()
# Remove nans:
df, Y = DataGuru.removenan(df, Y)
else:
df.dropna(inplace=True)
# Get the tsne model
# Code to run the classifier
X = df.values
# Get a standard scaler for the extracted data X
scaler = preprocessing.StandardScaler().fit(X)
X = scaler.transform(X)
# Train the classifier
numbers = findNumbers(target.data, 1)
if numbers != [] and numbers[0].data > 0:
num_clusters = int(numbers[0].data)
else:
num_clusters = 2 # If not specified use 2 clusters
kY = self.performOperation(X, num_clusters)
result_objects = []
if StatContainer.ground_truth is not None:
df_res = pd.DataFrame()
df_res['ground_truth'] = Y
df_res['clustering_result'] = kY
df_res.pivot_table(index=df_res.columns[0],
columns=df_res.columns[1],
aggfunc=np.size,
fill_value=0)
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
df_res = DataGuru.convertStrCols_toNumeric(df_res)
sns.heatmap(df_res, ax=ax)
win.show()
if data_frame is not None:
result_object = VizContainer.createResult(
win, data_frame, ['clstr.fig'])
else:
result_object = VizContainer.createResult(
win, array_datas, ['clstr.fig'])
result_objects.append(result_object)
result_object = ResultObject(kY, [], DataType.array,
CommandStatus.Success)
result_object.createName(cname,
command_name="clstr",
set_keyword_list=True)
result_objects.append(result_object)
return result_objects