def Plot(self, name_col1=7, name_col2=8, house_class=[]):
"""
Plot built scatter Plot two columns.
:param name_col1: first numeric column from dataset. Can accept index (int) and name (str) columns
:param name_col2: second numeric column from dataset. Can accept index (int) and name (str) columns
:param house_class: It's classes from Hogwarts House, default use all four classes.
:return:
"""
ds = DataSet(self.file_name)
col_mas_name = [name_col1, name_col2]
for i in range(2):
if (type(col_mas_name[i]) is str):
if col_mas_name[i] in ds.dataset[0]:
col_mas_name[i] = ds.dataset[0].index(col_mas_name[i])
else:
print('Error: bad name column')
return
for i in range(2):
if col_mas_name[i] < 0 or col_mas_name[i] >= len(ds.dataset[0]):
print("Error: This isn't column")
return
if not ds.isNumeric_columns(col_mas_name[i]):
print("Error: Input column must is numerics")
return
if self.size > (len(ds.dataset) - 1):
self.size = len(ds.dataset) - 1
col1 = ds.get_float_col(col_mas_name[0])
col2 = ds.get_float_col(col_mas_name[1])
color = {
'Ravenclaw': 'b',
'Gryffindor': 'r',
'Slytherin': 'g',
'Hufflepuff': 'yellow'
}
feature1 = {}
feature2 = {}
house_class = [i for i in house_class if i in set(ds.get_col(self.y_col))] if house_class else set(ds.get_col(self.y_col))
house_class = set(ds.get_col(self.y_col)) if not house_class else house_class
for i in house_class:
feature1[i] = []
feature2[i] = []
for i in range(1, len(ds.dataset)):
if ds.dataset[i][self.y_col] in house_class:
feature1[ds.dataset[i][self.y_col]].append(col1[i - 1])
feature2[ds.dataset[i][self.y_col]].append(col2[i - 1])
for i in feature1.keys():
plot.scatter(feature1[i][:self.size], feature2[i][:self.size], c=color[i], alpha=0.5, label=i)
if self.legend:
plot.legend(loc='upper right')
plot.ylabel(ds.dataset[0][col_mas_name[1]])
plot.xlabel(ds.dataset[0][col_mas_name[0]])
plot.title('Scatter Plot')
plot.savefig('datasets/scatter_plot.png')
plot.show()
def Plot(self):
ds = DataSet(self.file_name)
ds.find_numeric_label()
if self.max_nb_columns > (len(ds.numeric_columns)):
self.max_nb_columns = len(ds.numeric_columns)
color = {
'Ravenclaw': 'b',
'Gryffindor': 'r',
'Slytherin': 'g',
'Hufflepuff': 'yellow'
}
fig, ax = plot.subplots(self.max_nb_columns, self.max_nb_columns, figsize=self.fig_size)
fig.tight_layout()
N = self.max_nb_columns
for i in range(N):
col1 = ds.get_float_col(ds.numeric_columns[i])[:self.size]
for j in range(N):
col2 = ds.get_float_col(ds.numeric_columns[j])[:self.size]
feature1 = {}
feature2 = {}
for k in set(ds.get_col(self.y_col)):
feature1[k] = []
feature2[k] = []
for k in range(1, len(ds.dataset[:self.size])):
feature1[ds.dataset[k][self.y_col]].append(col1[k - 1])
feature2[ds.dataset[k][self.y_col]].append(col2[k - 1])
if i == 0:
ax[i, j].xaxis.set_label_position('top')
ax[i, j].set_xlabel(ds.dataset[0][ds.numeric_columns[j]], rotation=0)
if j == 0:
ax[i, j].set_ylabel(ds.dataset[0][ds.numeric_columns[i]], rotation=0)
if (i == j):
statistic = Math_calculat(col1)
bins = np.linspace(statistic.Quartile(0), statistic.Quartile(1))
for k in feature1.keys():
ax[i, j].hist(feature1[k], bins, facecolor=color[k], alpha=0.5, label=k)
else:
for k in feature1.keys():
ax[i, j].scatter(feature1[k], feature2[k], c=color[k], alpha=0.5, label=k)
ax[i, j].tick_params(labelbottom=False)
ax[i, j].tick_params(labelleft=False)
if self.legend:
plot.legend(loc='lower right')
plot.savefig('datasets/pair_plot.png')
plot.show()
def Plot(self, col_nb):
ds = DataSet(self.file_name)
if (type(col_nb) is str):
if col_nb in ds.dataset[0]:
col_nb = ds.dataset[0].index(col_nb)
else:
print('Error with name column')
return
if not ds.isNumeric_columns(col_nb):
print("Input column must is numerics")
return
col = ds.get_float_col(col_nb)
statistic = Math_calculat(col)
bins = np.linspace(statistic.Quartile(0), statistic.Quartile(1),
self.size)
color = {
'Ravenclaw': 'b',
'Gryffindor': 'r',
'Slytherin': 'g',
'Hufflepuff': 'yellow'
}
feature = {}
for i in set(ds.get_col(self.y_col)):
feature[i] = []
for i in range(1, len(ds.dataset)):
feature[ds.dataset[i][self.y_col]].append(col[i - 1])
for i in feature.keys():
plot.hist(feature[i], bins, facecolor=color[i], alpha=0.5, label=i)
if self.legend:
plot.legend(loc='upper right')
plot.ylabel('Frequency')
plot.xlabel('Value')
plot.title('Histogram')
plot.savefig('datasets/histogram.png')
plot.show()