mapdata 3.19.0__tar.gz → 3.21.0__tar.gz

{mapdata-3.19.0/mapdata.egg-info → mapdata-3.21.0}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.1
 Name: mapdata
-Version: 3.19.0
+Version: 3.21.0
 Summary: An interactive map and table explorer for geographic coordinates in a spreadsheet, CSV file, or database that includes data plotting and statistical summaries
 Home-page: https:/hg.sr.ht/~rdnielsen/mapdata
 Author: Dreas Nielsen
 Author-email: cortice@tutanota.com
 License: GPL
-Keywords: Map,Locations,CRS,CSV,Spreadsheet,Database,PNG,JPG,Postscript
+Keywords: Map,Locations,CRS,CSV,Spreadsheet,Database,Statistics,Plotting,PNG,JPG,Postscript
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Environment :: X11 Applications
@@ -24,21 +24,6 @@ Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: tkintermapview
-Requires-Dist: pyproj
-Requires-Dist: jenkspy
-Requires-Dist: odfpy
-Requires-Dist: openpyxl
-Requires-Dist: xlrd
-Requires-Dist: matplotlib
-Requires-Dist: seaborn
-Requires-Dist: loess
-Requires-Dist: statsmodels
-Requires-Dist: scipy
-Requires-Dist: scikit-learn
-Requires-Dist: pymannkendall
-Requires-Dist: umap-learn
-Requires-Dist: pynndescent
 
 
 *mapdata.py* is a data explorer for data sets containing geographic coordinates.  Data can be read from a CSV file, spreadsheet, or database.  Both a map and a data

{mapdata-3.19.0 → mapdata-3.21.0}/mapdata/mapdata.py

@@ -24,8 +24,8 @@
 #
 # ==================================================================
 
-version = "3.19.0"
-vdate = "2026-02-13"
+version = "3.21.0"
+vdate = "2026-03-17"
 
 copyright = "2023-2026"
 
@@ -1332,12 +1332,14 @@ def enable_if(widget, tf_val):
 	widget["state"] = tk.NORMAL if tf_val else tk.DISABLED
 
 def chosen_dataset(maingui, column_list, selected_only):
+	# Returns the dataset as a column-oriented list of lists.
 	if selected_only:
 		return maingui.get_sel_data(column_list)
 	else:
 		return maingui.get_all_data(column_list)
 
 def chosen_dataset_and_ids(maingui, column_list, selected_only):
+	# Returns the dataset as a column-oriented list of lists.
 	if selected_only:
 		return maingui.get_sel_data(column_list), maingui.get_sel_rowids()
 	else:
@@ -3401,7 +3403,7 @@ class MapUI(object):
 	def get_all_rowids(self):
 		return self.tbl.get_children()
 	def get_sel_data(self, column_list):
-		# Plotting and statistics support.  Return data from selected rows for the specified columns, as a list of lists.
+		# Plotting and statistics support.  Return data from selected rows for the specified columns, as a list of column-oriented lists.
 		res = [[] for _ in column_list]
 		indices = [self.headers.index(c) for c in column_list]
 		for sel_row in self.tbl.selection():
@@ -4015,6 +4017,14 @@ class MapUI(object):
 		dlg = UniqueValuesDialog(self, self.data_types)
 		dlg.show()
 
+	def show_missing_byrow(self, args=None):
+		dlg = MissingByRowDialog(self, self.data_types)
+		dlg.show()
+
+	def show_missing_byvariable(self, args=None):
+		dlg = MissingByVariableDialog(self, self.data_types)
+		dlg.show()
+
 	def add_rowid(self, args=None):
 		dlg = AddRowIDDialog(self, self.data_types)
 		colname, prefix = dlg.show()
@@ -4523,6 +4533,8 @@ class MapUI(object):
 		tbl_menu.add_command(label="Hide/show columns", command = self.hide_columns, underline=0)
 		tbl_menu.add_command(label="Counts by location", command=self.counts_by_loc, underline=0)
 		tbl_menu.add_command(label="Unique values", command=self.unique_data_values, underline=3)
+		tbl_menu.add_command(label="Missing by row", command=self.show_missing_byrow, underline=0)
+		tbl_menu.add_command(label="Missing by variable", command=self.show_missing_byvariable, underline=11)
 		tbl_menu.add_command(label="Find candidate keys", command=self.find_candkeys, underline=0)
 		tbl_menu.add_command(label="Find duplicate rows", command=self.find_duprows, underline=3)
 		tbl_menu.add_command(label="Test cardinality", command=self.cardinality_test, underline=10)
@@ -6733,6 +6745,15 @@ class UniqueValuesDialog(Dialog):
 		self.data_labels = None
 		self.dlg.bind("<Control-s>")
 
+		# Top controls
+		self.sel_only_var, self.sel_only_ck = add_sel_only(self.ctrl_frame, 0, 0, self.q_recalc)
+		self.indiv_var = tk.StringVar(self.ctrl_frame, "0")
+		indiv_ck = ttk.Checkbutton(self.ctrl_frame, text="Individually", command=self.q_recalc, variable=self.indiv_var,
+				onvalue="1", offvalue="0")
+		indiv_ck.grid(row=0, column=1, sticky=tk.W, padx=(6,3), pady=(3,3), columnspan=None)
+		self.ctrl_frame.columnconfigure(0, weight=0)
+		self.ctrl_frame.columnconfigure(1, weight=1)
+
 		# The content_frame encompasses the two panes of the variable frame and the content frame
 		frame_panes = ttk.PanedWindow(self.content_frame, orient=tk.HORIZONTAL, width=600)
 		frame_panes.grid(row=0, column=0, sticky=tk.NSEW)
@@ -6741,7 +6762,7 @@ class UniqueValuesDialog(Dialog):
 		var_frame = tk.Frame(frame_panes, width=250, borderwidth=2, relief=tk.RIDGE)
 		var_frame.grid(row=0, column=0, sticky=tk.NSEW)
 		var_frame.rowconfigure(0, weight=1)
-		var_frame.columnconfigure(0, weight=1)
+		var_frame.columnconfigure(0, weight=1, minsize=200)
 		frame_panes.add(var_frame, weight=1)
 		# Add multi-select list of variables to the leftmost pane
 		varvals = [[v] for v in self.variables]
@@ -6775,20 +6796,48 @@ class UniqueValuesDialog(Dialog):
 
 	def q_recalc(self, *event, get_data=True):
 		self.clear_output()
-		if len(self.column_table.selection()) > 0 and get_data:
-			self.recalc()
+		if len(self.column_table.selection()) > 0:
+			self.get_data()
+			if self.rawdataset is not None and len(self.rawdataset[0]) > 0:
+				self.recalc()
 
-	def recalc(self):
-		column_list = []
+	def get_data(self):
+		# Get the selected data into 'dataset'
+		self.rawdataset = None
+		self.colnames = []
 		for sel_row in self.column_table.selection():
 			datarow = self.column_table.item(sel_row)["values"]
-			column_list.append(datarow[0])
-		dbcols = db_colnames(column_list)
-		colstr = ",".join(dbcols)
-		sqlcmd = f"select distinct {colstr}, count(*) as nrows from mapdata group by {colstr} order by {colstr};"
-		cur = data_db.cursor()
-		self.dataset = cur.execute(sqlcmd).fetchall()
-		self.data_labels = column_list + ["Count"]
+			self.colnames.append(datarow[0])
+		if len(self.colnames) > 0:
+			# Get either only the selected data or all data.
+			dataset = chosen_dataset(self.parent, self.colnames, self.sel_only_var.get()=='1')
+			if dataset is None or len(dataset[0]) == 0:
+				self.rawdataset = None
+				self.colnames = None
+			else:
+				self.rawdataset = dataset
+
+	def recalc(self):
+		if self.indiv_var.get()=='1':
+			counts = dict(zip(self.colnames, [0 for _ in range(len(self.colnames))]))
+			for i,col in enumerate(self.colnames):
+				counts[col] = len(set([x for x in self.rawdataset[i] if x is not None and str(x) != '']))
+			self.dataset = list(counts.items())
+			self.data_labels = ["Variable", "Count"]
+		else:
+			counts = {}
+			ds = columns_to_rows(self.rawdataset)
+			for row in ds:
+				trow = tuple(row)
+				if trow not in counts.keys():
+					counts[trow] = 1
+				else:
+					counts[trow] += 1
+			self.dataset = [list(k) for k in counts.keys()]
+			vals = list(counts.values())
+			for i in range(len(counts)):
+				self.dataset[i].append(vals[i])
+			self.data_labels = self.colnames + ["Count"]
 		tframe, tdata = treeview_table(self.values_frame, self.dataset, self.data_labels)
 		tframe.grid(row=0, column=0, sticky=tk.NSEW)
 		self.dlg.bind("<Control-s>", self.save_data)
@@ -6798,6 +6847,277 @@ class UniqueValuesDialog(Dialog):
 		self.dlg.wait_window(self.dlg)
 
 
+class MissingByRowDialog(Dialog):
+	def __init__(self, parent, column_specs):
+		self.parent = parent
+		self.column_specs = column_specs
+		self.auto_update = True
+		super().__init__("Rows with Missing Values",
+				"Select one or more variables from the left to see how many rows have 0, 1, 2, or more missing values for these variables.  A grouping variable may optionally be used.  Use Ctrl-click or Shift-click to select multiple rows.",
+				help_url="https://mapdata.readthedocs.io/en/latest/missing_by_row.html")
+		# Data
+		self.dataset = None
+		self.data_labels = None
+		self.all_columns = sorted([c[0] for c in self.column_specs])
+		self.categ_columns = sorted([c[0] for c in self.column_specs if c[1] in ("string", "boolean", "date", "timestamp")])
+		self.dnames = ["Group", "Missing values", "Number of rows"]
+		self.dlg.bind("<Control-s>")
+
+		# Top controls
+		self.sel_only_var, self.sel_only_ck = add_sel_only(self.ctrl_frame, 0, 0, self.q_recalc)
+		self.autoupdate_var = add_autoupdate(self.ctrl_frame, 0, 1, self.set_autoupdate)
+		self.ctrl_frame.columnconfigure(0, weight=0)
+		self.ctrl_frame.columnconfigure(1, weight=1)
+
+		# Two panes for the variable frame and the content frame
+		frame_panes = ttk.PanedWindow(self.content_frame, orient=tk.HORIZONTAL)
+		frame_panes.grid(row=0, column=0, sticky=tk.NSEW, padx=3, pady=3)
+
+		# Variable frame for list of columns/variables
+		var_frame = tk.Frame(frame_panes, borderwidth=2, relief=tk.RIDGE)
+		var_frame.grid(row=0, column=0, sticky=tk.NSEW)
+		var_frame.rowconfigure(0, weight=1)
+		var_frame.columnconfigure(0, weight=1)
+		frame_panes.add(var_frame, weight=1)
+		# Add multi-select list of variables to the leftmost pane
+		self.column_frame, self.column_table = treeview_table(var_frame, rowset=[[v] for v in self.all_columns], \
+				column_headers=['Variable'], select_mode=tk.EXTENDED, nrows=min(10, len(self.all_columns)))
+		self.column_frame.grid(row=0, column=0, sticky=tk.NSEW)
+		self.column_table.bind('<ButtonRelease-1>', self.q_recalc)
+
+		# Add an optional 'group by' variable selection
+		self.groupby_var = tk.StringVar(var_frame, "")
+		groupby_lbl = ttk.Label(var_frame, text="Group by:")
+		groupby_lbl.grid(row=1, column=0, sticky=tk.W, padx=(6,3), pady=(3,3))
+		self.groupby_sel = ttk.Combobox(var_frame, state="readonly", textvariable=self.groupby_var, 
+				values= [''] + self.categ_columns, width=24)
+		self.groupby_sel.grid(row=2, column=0, sticky=tk.W, padx=(12,3), pady=(3,3))
+		self.groupby_sel.bind("<<ComboboxSelected>>", self.q_recalc)
+
+		# output frame.  This contains a Treeview table with the counts of missing values.
+		self.output_frame = tk.Frame(frame_panes, borderwidth=3, relief=tk.RIDGE)
+		self.output_frame.grid(row=0, column=0, sticky=tk.NSEW)
+		self.output_frame.rowconfigure(0, weight=1)
+		self.output_frame.columnconfigure(0, weight=1)
+		frame_panes.add(self.output_frame, weight=12)
+	
+		# initialize content frame with headings, no data
+		self.clear_output()
+
+		# Buttons
+		add_help_close_buttons(self.dlg, self.btn_frame, self.do_help, self.do_close)
+
+	def clear_output(self):
+		for ctl in self.output_frame.winfo_children():
+			ctl.destroy()
+		clear_dlg_hotkeys(self.dlg)
+		self.dataset = None
+		self.missingdata = None
+		tframe, tdata = treeview_table(self.output_frame, [], self.dnames)
+		tframe.grid(row=0, column=0, sticky=tk.NSEW)
+
+	def q_recalc(self, *args):
+		if len(self.column_table.selection()) > 0:
+			self.clear_output()
+			self.get_data()
+		if self.dataset is not None and len(self.dataset[0]) > 0:
+			self.recalc()
+
+	def get_data(self):
+		# Get the selected data into 'dataset'
+		self.dataset = None
+		self.n_dataset_columns = 0
+		column_list = []
+		for sel_row in self.column_table.selection():
+			datarow = self.column_table.item(sel_row)["values"]
+			column_list.append(datarow[0])
+		if len(column_list) > 0:
+			self.n_dataset_columns = len(column_list)
+			if self.groupby_var.get() != "":
+				column_list.append(self.groupby_var.get())
+			# Get either only the selected data or all data.
+			dataset = chosen_dataset(self.parent, column_list, self.sel_only_var.get() == "1")
+			if dataset is None or len(dataset[0]) == 0:
+				self.dataset = None
+				self.data_labels = None
+			else:
+				self.dataset = dataset
+				self.data_labels = column_list
+
+	def recalc(self):
+		# Find the numbers of missing values of all selected rows.  This is accumulated as a dictionary
+		# with keys equal to numbers of missing values in a row and values of the number of rows with
+		# that number of missing values.
+		def incmissing(dic, n_missing):
+			if n_missing not in dic.keys():
+				dic[n_missing] = 0
+			dic[n_missing] = dic[n_missing] + 1
+
+		if self.data_labels is not None:
+			if self.groupby_var.get() == "":
+				missings = {}
+				for datarow in columns_to_rows(self.dataset):
+					incmissing(missings, sum(val == '' for val in datarow))
+				self.missingdata = sorted(list(zip(missings.keys(), missings.values())))
+				self.dnames = ["Missing", "Rows"]
+			else:
+				datasetdict = subset_by_groups(self.dataset[0:self.n_dataset_columns], self.dataset[self.n_dataset_columns])
+				self.missingdata = []
+				for grp in datasetdict.keys():
+					ds = columns_to_rows(datasetdict[grp])
+					missings = {}
+					for datarow in ds:
+						incmissing(missings, sum(val == '' for val in datarow))
+					self.missingdata.extend(sorted(list(zip([grp]*len(missings.keys()), missings.keys(), missings.values())), key=lambda x: x[1]))
+					self.dnames = ["Group", "Missing", "Rows"]
+		tframe, tdata = treeview_table(self.output_frame, self.missingdata, self.dnames)
+		tframe.grid(row=0, column=0, sticky=tk.NSEW)
+		self.dlg.bind("<Control-s>", self.save_data)
+	def set_autoupdate(self):
+		self.auto_update = self.autoupdate_var.get() == "1"
+		if self.auto_update:
+			self.q_recalc(None)
+	def save_data(self, *args):
+		export_data_table(self.dnames, self.missingdata, sheetname="Numbers of missing values")
+	def do_close(self, *args):
+		self.parent.remove_univar(self)
+		super().do_cancel(args)
+
+
+
+class MissingByVariableDialog(Dialog):
+	def __init__(self, parent, column_specs):
+		self.parent = parent
+		self.column_specs = column_specs
+		self.auto_update = True
+		super().__init__("Variables with Missing Values",
+				"Select one or more variables from the left to see how many missing values each has.  A grouping variable may optionally be used.  Use Ctrl-click or Shift-click to select multiple rows.",
+				help_url="https://mapdata.readthedocs.io/en/latest/missing_by_variable.html")
+		# Data
+		self.dataset = None
+		self.data_labels = None
+		self.all_columns = sorted([c[0] for c in self.column_specs])
+		self.categ_columns = sorted([c[0] for c in self.column_specs if c[1] in ("string", "boolean", "date", "timestamp")])
+		self.dnames = ["Variable", "Missing"]
+		self.dlg.bind("<Control-s>")
+
+		# Top controls
+		self.sel_only_var, self.sel_only_ck = add_sel_only(self.ctrl_frame, 0, 0, self.q_recalc)
+		self.autoupdate_var = add_autoupdate(self.ctrl_frame, 0, 1, self.set_autoupdate)
+		self.ctrl_frame.columnconfigure(0, weight=0)
+		self.ctrl_frame.columnconfigure(1, weight=1)
+
+		# Two panes for the variable frame and the content frame
+		frame_panes = ttk.PanedWindow(self.content_frame, orient=tk.HORIZONTAL)
+		frame_panes.grid(row=0, column=0, sticky=tk.NSEW, padx=3, pady=3)
+
+		# Variable frame for list of all columns/variables
+		var_frame = tk.Frame(frame_panes, borderwidth=2, relief=tk.RIDGE)
+		var_frame.grid(row=0, column=0, sticky=tk.NSEW)
+		var_frame.rowconfigure(0, weight=1)
+		var_frame.columnconfigure(0, weight=1)
+		frame_panes.add(var_frame, weight=1)
+		# Add multi-select list of variables to the leftmost pane
+		self.column_frame, self.column_table = treeview_table(var_frame, rowset=[[v] for v in self.all_columns], \
+				column_headers=['Variable'], select_mode=tk.EXTENDED, nrows=min(10, len(self.all_columns)))
+		self.column_frame.grid(row=0, column=0, sticky=tk.NSEW)
+		self.column_table.bind('<ButtonRelease-1>', self.q_recalc)
+
+		# Add an optional 'group by' variable selection
+		self.groupby_var = tk.StringVar(var_frame, "")
+		groupby_lbl = ttk.Label(var_frame, text="Group by:")
+		groupby_lbl.grid(row=1, column=0, sticky=tk.W, padx=(6,3), pady=(3,3))
+		self.groupby_sel = ttk.Combobox(var_frame, state="readonly", textvariable=self.groupby_var, 
+				values= [''] + self.categ_columns, width=24)
+		self.groupby_sel.grid(row=2, column=0, sticky=tk.W, padx=(12,3), pady=(3,3))
+		self.groupby_sel.bind("<<ComboboxSelected>>", self.q_recalc)
+
+		# Output frame.  This contains a Treeview table with the counts of missing values.
+		self.output_frame = tk.Frame(frame_panes, borderwidth=3, relief=tk.RIDGE)
+		self.output_frame.grid(row=0, column=0, sticky=tk.NSEW)
+		self.output_frame.rowconfigure(0, weight=1)
+		self.output_frame.columnconfigure(0, weight=1)
+		frame_panes.add(self.output_frame, weight=12)
+	
+		# initialize content frame with headings, no data
+		self.clear_output()
+
+		# Buttons
+		add_help_close_buttons(self.dlg, self.btn_frame, self.do_help, self.do_close)
+
+	def clear_output(self):
+		for ctl in self.output_frame.winfo_children():
+			ctl.destroy()
+		clear_dlg_hotkeys(self.dlg)
+		self.dataset = None
+		self.missingdata = None
+		tframe, tdata = treeview_table(self.output_frame, [], self.dnames)
+		tframe.grid(row=0, column=0, sticky=tk.NSEW)
+
+	def q_recalc(self, *args):
+		if len(self.column_table.selection()) > 0:
+			self.clear_output()
+			self.get_data()
+		if self.dataset is not None and len(self.dataset[0]) > 0:
+			self.recalc()
+
+	def get_data(self):
+		# Get the selected data into 'dataset'
+		self.dataset = None
+		self.n_dataset_columns = 0
+		column_list = []
+		for sel_row in self.column_table.selection():
+			datarow = self.column_table.item(sel_row)["values"]
+			column_list.append(datarow[0])
+		if len(column_list) > 0:
+			self.n_dataset_columns = len(column_list)
+			if self.groupby_var.get() != "":
+				column_list.append(self.groupby_var.get())
+			# Get either only the selected data or all data.
+			dataset = chosen_dataset(self.parent, column_list, self.sel_only_var.get() == "1")
+			if dataset is None or len(dataset[0]) == 0:
+				self.dataset = None
+				self.data_labels = None
+			else:
+				self.dataset = dataset
+				self.data_labels = column_list
+
+	def recalc(self):
+		# Find the numbers of missing values of all selected variables.
+		if self.data_labels is not None:
+			if self.groupby_var.get() == "":
+				# Output is two columns, one with the variable name and one with the number of missing values.
+				n_missing = []
+				for col in self.dataset:
+					n_missing.append(sum(val == '' for val in col))
+				self.missingdata = sorted(list(zip(self.data_labels, n_missing)))
+				self.dnames = ["Variable", "Missing"]
+			else:
+				# Output is a table with groups in rows, variables in columns, missing values in cells
+				datasetdict = subset_by_groups(self.dataset[0:self.n_dataset_columns], self.dataset[self.n_dataset_columns])
+				self.missingdata = []
+				for grp in datasetdict.keys():
+					ds = datasetdict[grp]
+					n_missing = [grp]
+					for col in ds:
+						n_missing.append(sum(val == '' for val in col))
+					self.missingdata.append(n_missing)
+				self.dnames = ["Group"] + self.data_labels[:-1]
+		tframe, tdata = treeview_table(self.output_frame, self.missingdata, self.dnames)
+		tframe.grid(row=0, column=0, sticky=tk.NSEW)
+		self.dlg.bind("<Control-s>", self.save_data)
+	def set_autoupdate(self):
+		self.auto_update = self.autoupdate_var.get() == "1"
+		if self.auto_update:
+			self.q_recalc(None)
+	def save_data(self, *args):
+		export_data_table(self.dnames, self.missingdata, sheetname="Numbers of missing values")
+	def do_close(self, *args):
+		self.parent.remove_univar(self)
+		super().do_cancel(args)
+
+
+
 class SelNonMissingDialog(Dialog):
 	def __init__(self, column_specs):
 		super().__init__("Select Non-Missing Values",
@@ -6948,7 +7268,7 @@ class PlotDialog(Dialog):
 			plot_types.append("Date range by category")
 		plot_types.extend(["Empirical CDF", "Histogram", "Kernel density (KD) plot", "Line plot", "Mean by category",
 					"Min-max by bin", "Min-max by category", "Normal Q-Q plot", "Pareto chart", "Scatter plot", "Stripchart",
-					"Total by category", "Violin plot", "Y range plot"])
+					"Total by category", "Violin plot", "Y range plot", "Zipf's Law"])
 		self.type_sel = ttk.Combobox(self.ctrl_frame, state="readonly", textvariable=self.type_var, width=20, height=21, values=plot_types)
 		self.type_sel.grid(row=0, column=1, columnspan=2, sticky=tk.W, padx=(3,6), pady=(3,3))
 		self.type_sel["state"] = tk.NORMAL
@@ -7174,9 +7494,11 @@ class PlotDialog(Dialog):
 		elif plot_type == "Min-max by category":
 			self.x_sel["state"] = "readonly"
 			self.x_sel["values"] = self.quant_columns
-			self.xlog_ck["state"] = tk.NORMAL
 			self.y_sel["state"] = "readonly"
 			self.y_sel["values"] = self.categ_columns2
+		elif plot_type == "Zipf's Law":
+			self.x_sel["state"] = "readonly"
+			self.x_sel["values"] = sorted([c[0] for c in self.column_specs if c[1] == "string"])
 		else:
 			self.x_sel["state"] = "readonly"
 			self.x_sel["values"] = self.quant_columns
@@ -7197,7 +7519,7 @@ class PlotDialog(Dialog):
 		# Conditionally (re)draw the plot.
 		plot_type = self.type_var.get()
 		can_redraw = (plot_type in ("Count by category", "Empirical CDF", "Normal Q-Q plot", "Breaks groups", "Breaks optimum", \
-				"Histogram", "Pareto chart") and self.x_var.get() != '') \
+				"Histogram", "Pareto chart", "Zipf's Law") and self.x_var.get() != '') \
 				or (plot_type in ("Scatter plot", "Line plot", "Min-max by bin", "Min-max by category", "Y range plot") and \
 				self.x_var.get() != '' and self.y_var.get() != '') \
 				or (plot_type in ("Box plot", "Kernel density (KD) plot", "Stripchart", "Violin plot") and self.x_var.get() != '') \
@@ -7293,6 +7615,19 @@ class PlotDialog(Dialog):
 				x_counts = [counter[k] for k in x_vals]
 				self.plot_data = [x_vals, x_counts]
 				self.plot_data_labels = [self.data_labels[0], "Count"]
+			elif plot_type == "Zipf's Law":
+				counter = collections.Counter(self.dataset[0])
+				zcts = sorted(list(zip(counter.values(), counter.keys())), key=lambda x: x[0], reverse=True)
+				zd = list(zip(*zcts))
+				zdata = [list(zd[1]), list(zd[0])]
+				zdata.append(list(range(1, len(zdata[0])+1)))
+				tot = sum(zdata[1])
+				zdata.append([x/tot for x in zdata[1]])
+				zdata.append([math.log10(x) for x in zdata[2]])
+				zdata.append([math.log10(x) for x in zdata[3]])
+				self.plot_data = zdata
+				self.plot_data_labels = [self.data_labels[0], "Count", "Rank", "Frequency", "Log10_Rank", "Log10_Frequency"]
+				self.xlog_ck["state"] = tk.DISABLED
 			elif plot_type in ("Box plot", "Histogram", "Kernel density (KD) plot", "Stripchart", "Violin plot"):
 				if self.groupby_var.get() != '':
 					self.plot_data_labels, self.plot_data = spread_by_groups(self.dataset[1], self.dataset[0])
@@ -7869,7 +8204,7 @@ class PlotDialog(Dialog):
 				self.plot.axes.plot([pmin, pmax], [pmin, pmax])
 				self.plot.set_axis_labels(self.xlabel or self.plot_data_labels[2], self.ylabel or self.plot_data_labels[1])
 			elif plot_type == "Pareto chart":
-				groups = self.plot_data[0]
+				groups = [str(g) for g in self.plot_data[0]]
 				grp_lbls = []
 				for g in groups:
 					if wrap_at_underscores:
@@ -7983,6 +8318,13 @@ class PlotDialog(Dialog):
 					else:
 						sns.violinplot({self.x_var.get(): self.dataset[0]}, x=self.x_var.get(), alpha=self.alpha, ax=self.plot_axes)
 						self.plot.set_axis_labels(self.ylabel or self.data_labels[0], self.xlabel or self.x_var.get())
+			elif plot_type == "Zipf's Law":
+				self.plot.axes.set_xscale('log')
+				self.plot.axes.set_yscale('log')
+				self.plot.axes.grid(visible=True, color="0.8", linestyle="dotted", which='both', axis='both')
+				self.plot.axes.plot(self.plot_data[2], self.plot_data[3], alpha=self.alpha)
+				self.plot.set_axis_labels(self.plot_data_labels[2], self.xlabel or self.plot_data_labels[3])
+				self.plot_title = self.data_labels[0]
 			if self.plot_title is not None:
 				self.plot.axes.set_title(self.plot_title)
 				self.plot.axes.title.set_visible(True)
@@ -13351,7 +13693,7 @@ class NMFUnmixingDialog(Dialog):
 		frame_panes.grid(row=0, column=0, sticky=tk.NSEW)
 
 		# Variable frame for list of quantitative columns/variables
-		var_frame = tk.Frame(frame_panes, borderwidth=2, relief=tk.RIDGE)
+		var_frame = tk.Frame(frame_panes, width=250, borderwidth=2, relief=tk.RIDGE)
 		var_frame.grid(row=0, column=0, sticky=tk.NSEW)
 		var_frame.rowconfigure(0, weight=1)
 		var_frame.columnconfigure(0, weight=1, minsize=200)

{mapdata-3.19.0 → mapdata-3.21.0/mapdata.egg-info}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.1
 Name: mapdata
-Version: 3.19.0
+Version: 3.21.0
 Summary: An interactive map and table explorer for geographic coordinates in a spreadsheet, CSV file, or database that includes data plotting and statistical summaries
 Home-page: https:/hg.sr.ht/~rdnielsen/mapdata
 Author: Dreas Nielsen
 Author-email: cortice@tutanota.com
 License: GPL
-Keywords: Map,Locations,CRS,CSV,Spreadsheet,Database,PNG,JPG,Postscript
+Keywords: Map,Locations,CRS,CSV,Spreadsheet,Database,Statistics,Plotting,PNG,JPG,Postscript
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Environment :: X11 Applications
@@ -24,21 +24,6 @@ Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: tkintermapview
-Requires-Dist: pyproj
-Requires-Dist: jenkspy
-Requires-Dist: odfpy
-Requires-Dist: openpyxl
-Requires-Dist: xlrd
-Requires-Dist: matplotlib
-Requires-Dist: seaborn
-Requires-Dist: loess
-Requires-Dist: statsmodels
-Requires-Dist: scipy
-Requires-Dist: scikit-learn
-Requires-Dist: pymannkendall
-Requires-Dist: umap-learn
-Requires-Dist: pynndescent
 
 
 *mapdata.py* is a data explorer for data sets containing geographic coordinates.  Data can be read from a CSV file, spreadsheet, or database.  Both a map and a data

{mapdata-3.19.0 → mapdata-3.21.0}/setup.py

@@ -9,7 +9,7 @@ symbol_files = glob.glob("mapdata/symbols/16x16/*.xbm") + glob.glob("mapdata/sym
 			glob.glob("mapdata/symbols/24x24/*.xbm") + glob.glob("mapdata/symbols/28x28/*.xbm")
 
 setuptools.setup(name='mapdata',
-	version='3.19.0',
+	version='3.21.0',
 	description="An interactive map and table explorer for geographic coordinates in a spreadsheet, CSV file, or database that includes data plotting and statistical summaries",
 	author='Dreas Nielsen',
 	author_email='cortice@tutanota.com',
@@ -36,7 +36,7 @@ setuptools.setup(name='mapdata',
 		'Topic :: Office/Business',
 		'Topic :: Scientific/Engineering'
 		],
-	keywords=['Map', 'Locations', 'CRS', 'CSV', 'Spreadsheet', 'Database', 'PNG', 'JPG', 'Postscript'],
+	keywords=['Map', 'Locations', 'CRS', 'CSV', 'Spreadsheet', 'Database', 'Statistics', 'Plotting', 'PNG', 'JPG', 'Postscript'],
 	long_description_content_type="text/markdown",
 	long_description=long_description
 	)