def __init__(self, dataset):
self.mean = mean(dataset)
self.std = std(dataset, self.mean)
self.percentiles = percentiles(dataset, PERCENTILES)
self.calculated_percentiles = [
self.mean - 2 * self.std, self.mean - self.std,
self.mean - 0.67 * self.std, self.mean,
self.mean + 0.67 * self.std, self.mean + self.std,
self.mean + 2 * self.std
]
self.max = max(Dataset.get_num_column_or_list(dataset))
self.min = min(Dataset.get_num_column_or_list(dataset))
self.is_normal = self._is_normal(self.percentiles,
self.calculated_percentiles)
self.length = len(dataset)
def hist(dataset, **kwargs):
defaults = {
'grid': False,
'xlabel': '',
'ylabel': '',
'title': '',
'output': None,
}
plot_params = {
'bins': 20,
'normed': 1,
'facecolor': 'green',
'alpha': 0.75,
}
plot_params.update(kwargs)
[plot_params.pop(k) for k in defaults if k in plot_params]
defaults.update(kwargs)
values = list(Dataset.get_num_column_or_list(dataset))
n, bins, patches = plt.hist(values, **plot_params)
plt.xlabel(defaults['xlabel'])
plt.ylabel(defaults['ylabel'])
plt.title(defaults['title'])
plt.grid(defaults['grid'])
filename = defaults['output'] or get_tmp_file_name('.png')
plt.savefig(filename)
return filename
def hist(dataset, **kwargs):
defaults = {
'grid': False,
'xlabel': '',
'ylabel': '',
'title': '',
'output': None,
}
graph_params = {
'bins': 20,
'normed': 1,
'facecolor': 'green',
'alpha': 0.75,
}
graph_params.update(kwargs)
defaults.update(kwargs)
[graph_params.pop(k) for k in defaults if k in graph_params]
values = list(Dataset.get_num_column_or_list(dataset))
n, bins, patches = plt.hist(values, **graph_params)
plt.xlabel(defaults['xlabel'])
plt.ylabel(defaults['ylabel'])
plt.title(defaults['title'])
plt.grid(defaults['grid'])
filename = defaults['output'] or get_tmp_file_name('.png')
plt.savefig(filename)
return filename
def __init__(self, dataset):
self.mean = mean(dataset)
self.std = std(dataset, self.mean)
self.percentiles = percentiles(dataset, PERCENTILES)
self.calculated_percentiles = [
self.mean - 2 * self.std,
self.mean - self.std,
self.mean - 0.67 * self.std,
self.mean,
self.mean + 0.67 * self.std,
self.mean + self.std,
self.mean + 2 * self.std]
self.max = max(Dataset.get_num_column_or_list(dataset))
self.min = min(Dataset.get_num_column_or_list(dataset))
self.is_normal = self._is_normal(
self.percentiles, self.calculated_percentiles)
self.length = len(dataset)
def mean(dataset):
values = Dataset.get_num_column_or_list(dataset)
return sum(values) / float(len(dataset))
def percentiles(dataset, vals):
n = len(dataset)
values = list(Dataset.get_num_column_or_list(dataset))
values.sort()
return [_percentile(values, n, p) for p in vals]
def std(dataset, m=None):
n = len(dataset)
values = Dataset.get_num_column_or_list(dataset)
if m is None:
m = mean(dataset)
return (sum((i - m) ** 2 for i in values) / float(n)) ** 0.5
def mean(dataset):
values = Dataset.get_num_column_or_list(dataset)
return sum(values) / float(len(dataset))
def percentiles(dataset, vals):
n = len(dataset)
values = list(Dataset.get_num_column_or_list(dataset))
values.sort()
return [_percentile(values, n, p) for p in vals]
def std(dataset, m=None):
n = len(dataset)
values = Dataset.get_num_column_or_list(dataset)
if m is None:
m = mean(dataset)
return (sum((i - m)**2 for i in values) / float(n))**0.5
