Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

perf: allow users to select empty columns，optimized contour plotting for the decomposition. #325

Closed
wants to merge 2 commits into from
Closed

perf: allow users to select empty columns，optimized contour plotting for the decomposition. #325

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
27968ad
perf: allow users to select empty columns.
luzhu-star Mar 24, 2024
ca58ad4
perf: optimized contour plotting for the decomposition.
luzhu-star Mar 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions geochemistrypi/data_mining/data/data_readiness.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,9 @@ def create_sub_data_set(data: pd.DataFrame) -> pd.DataFrame:
"@input: "
)
)

allow_empty_columns = input("Do you want to include empty columns? (yes/no): ").strip().lower() == "yes"

while True:
if ("【" in sub_data_set_columns_range) or ("】" in sub_data_set_columns_range):
print("There is a problem with the format of the parentheses entered !")
Expand Down Expand Up @@ -242,9 +245,10 @@ def create_sub_data_set(data: pd.DataFrame) -> pd.DataFrame:
df_test = pd.DataFrame(data_checking[i])
test_columns = df_test.columns
v_value = int(df_test.isnull().sum())
if v_value == len(df_test):
if not allow_empty_columns and v_value == len(df_test):
print(f"Warning: The selected column {df_test.columns.values} is an empty column!")
judge = True
sub_data_set_columns_range = str(input("Please re-enter the data range you want to process:\n@input: "))
break
elif df_test[test_columns[0]].dtype in ["int64", "float64"]:
continue
else:
Expand All @@ -257,6 +261,8 @@ def create_sub_data_set(data: pd.DataFrame) -> pd.DataFrame:

# select designated column
sub_data_set = data.iloc[:, sub_data_set_columns_selected]
if not allow_empty_columns:
sub_data_set = sub_data_set.dropna(axis=1, how="all")
show_data_columns(sub_data_set.columns, sub_data_set_columns_selected)
return sub_data_set

Expand Down
14 changes: 10 additions & 4 deletions geochemistrypi/data_mining/model/func/algo_decomposition/_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,11 +101,17 @@ def plot_contour(data: pd.DataFrame, algorithm_name: str) -> None:
algorithm_name : str
The name of the dimensionality reduction algorithm.
"""
quantile_threshold = 0.9
x_upper_threshold = data.iloc[:, 0].quantile(quantile_threshold)
y_upper_threshold = data.iloc[:, 1].quantile(quantile_threshold)
filtered_data = data[(data.iloc[:, 0] <= x_upper_threshold) & (data.iloc[:, 1] <= y_upper_threshold)]

# Calculate the density
x = data.iloc[:, 0]
y = data.iloc[:, 1]
xmin, xmax = x.min(), x.max()
ymin, ymax = y.min(), y.max()
x = filtered_data.iloc[:, 0]
y = filtered_data.iloc[:, 1]
buffer = max(x.max() - x.min(), y.max() - y.min()) * 0.05
xmin, xmax = x.min() - buffer, x.max() + buffer
ymin, ymax = y.min() - buffer, y.max() + buffer

xx, yy = np.mgrid[xmin:xmax:100j, ymin:ymax:100j]
positions = np.vstack([xx.ravel(), yy.ravel()])
Expand Down
Loading