mapdata 1.10.1__tar.gz → 2.0.2__tar.gz

{mapdata-1.10.1/mapdata.egg-info → mapdata-2.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapdata
-Version: 1.10.1
+Version: 2.0.2
 Summary: An interactive map and table explorer for geographic coordinates in a CSV file
 Home-page: https://osdn.net/project/mapdata/
 Author: Dreas Nielsen
@@ -27,6 +27,7 @@ Requires: pyproj
 Requires: odfpy
 Requires: openpyxl
 Requires: xlrd
+Requires: matplotlib
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
@@ -63,6 +64,12 @@ export the map to an image file, and quit.
 
 Selected rows in the data table can be exported to a CSV or spreadsheet file.
 
+Data can also be displayed in several different types of plots: box plots, scatter
+plots, line charts, and counts of categorical and quantitative variables.  Plots
+can use either all data or only data values that are selected in the map and
+table.  Plots have a live connection to the data table, so when selections are
+changed the plots are automatically updated.
+
 
 Complete documentation is at [https://mapdata.osdn.io](https://mapdata.osdn.io).
 

{mapdata-1.10.1 → mapdata-2.0.2}/README.md

@@ -30,6 +30,12 @@ export the map to an image file, and quit.
 
 Selected rows in the data table can be exported to a CSV or spreadsheet file.
 
+Data can also be displayed in several different types of plots: box plots, scatter
+plots, line charts, and counts of categorical and quantitative variables.  Plots
+can use either all data or only data values that are selected in the map and
+table.  Plots have a live connection to the data table, so when selections are
+changed the plots are automatically updated.
+
 
 Complete documentation is at [https://mapdata.osdn.io](https://mapdata.osdn.io).
 

{mapdata-1.10.1 → mapdata-2.0.2}/mapdata/mapdata.py

@@ -3,7 +3,9 @@
 # mapdata.py
 #
 # PURPOSE
-#	Create a simple interactive map of data points in Tkinter.
+#	Display a simple interactive map of data points, allowing points to
+#	be highlighted by clicking on the map or table or by querying,
+#	and allowing some simple data plots.
 #
 # COPYRIGHT AND LICENSE
 #	Copyright (c) 2023, R. Dreas Nielsen
@@ -17,72 +19,13 @@
 # 	GNU General Public License for more details.
 # 	The GNU General Public License is available at <http://www.gnu.org/licenses/>
 #
-# NOTES
-#	1.
-#
 # AUTHOR
 #	Dreas Nielsen (RDN)
 #
-# HISTORY
-#	 Date		 Remarks
-#	----------	-----------------------------------------------------
-#	2023-03-27	Created.  RDN.
-#	2023-04-16	Added CsvFile() and treeview_table(), and began
-#				MapUI().  RDN.
-#	2023-04-24	Completed MapUI() and tested to success.
-#	2023-04-25	Added map control buttons to zoom, focus, and un-select.  RDN.
-#	2023-04-27	Adapted to missing coordinates in the data table and
-#				to avoid an exception when table columns are resized but
-#				no row selected.  RDN.
-#	2023-04-29	Allowed single or multiple selection, and zoom to
-#				selected markers when multiple are selected.
-#				Added menu items to save selected table rows and to save
-#				the map as a Postscript document.  Added menu item to
-#				change the marker used.  RDN.
-#	2023-04-30	Reduced the set of colors that can be selected for the marker.  RDN.
-#	2023-05-01	Added a Quit option to the file menu and removed the bottom
-#				button frame.  Implemented reading of default and custom
-#				configuration files, and import of an .xbm symbol file.
-#				Enabled operation as a full GUI application--note that this
-#				requires a change to the command-line filename from an argument
-#				to an option.  When the application is started without a command
-#				line specification, PIL emits error messages to stderr but
-#				ordinarily this is not seen and the program's operation is
-#				unaffected.  RDN.
-#	2023-05-02	Changed the default label color and locations, added global
-#				settings for the location symbol, color, font, font size,
-#				font color, and font location, and allowed all of those to
-#				be changed via the configuration file.  RDN.
-#	2023-05-08	Added conversion of other coordinate reference systems to 4326.  RDN.
-#	2023-05-09	Added ability to switch CRSs for the same data.  RDN.
-#	2023-05-11	Fixed map controls when resizing.  Added command-line arguments
-#				to export the map and quit.  RDN.
-#	2023-05-12	Added export of configuration settings.  Cleaned up help
-#				dialogs.  RDN.
-#	2023-05-14	Put the map and table in a PanedWindow.  RDN.
-#	2023-05-16	Fixed label wrapping in Windows on the CSV open dialog.  Corrected
-#				binding of Return and Escape keys to dialog button actions.  Adujsted
-#				button position in MsgDialog.  RDN.
-#	2023-05-24	Modified dialogs, added 'Help' buttons.  RDN.
-#	2023-05-30	Partially implemented data query dialog--functional, but no sidebar
-#				listing column values.  RDN.
-#	2023-05-31	Added sidebar listing column values to the data query dialog.
-#				Double-clicking on a listed column value adds it to the end of the
-#				SQL entry widget.  RDN.
-#	2023-06-01	Modified to select all rows in the table with the same lat/lon as
-#				a clicked map location, even when multiselect=0.  RDN.
-#	2023-06-02	Added 'Invert' menu option on new 'Selections' menu.  RDN.
-#	2023-06-03	Centered dialogs, made dialogs un-resizable, and added menu
-#				hotkeys.  RDN.
-#	2023-06-04	Added menu option to import data from spreadsheets.  RDN.
-#	2023-06-08	Added menu option to import data from databases.  RDN.
-#	2023-06-09	Added DuckDB as a data source and modifed startup to
-#				allow spreadsheets to be selected on the command line.  RDN.
-#	2023-06-12	Corrected Help links for spreadsheet and database dialogs.  RDN.
 # ==================================================================
 
-version = "1.10.1"
-vdate = "2023-06-12"
+version = "2.0.2"
+vdate = "2023-06-15"
 
 copyright = "2023"
 
@@ -96,8 +39,13 @@ from configparser import ConfigParser
 import csv
 import re
 import datetime
+import dateutil.parser as dateparser
 import time
+import math
+import collections
 import webbrowser
+import threading
+import queue
 import sqlite3
 import tempfile
 import tkinter as tk
@@ -113,6 +61,10 @@ import odf.number
 import odf.style
 import xlrd
 import openpyxl
+import matplotlib
+matplotlib.use('TkAgg')
+from matplotlib.figure import Figure
+from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg, NavigationToolbar2Tk
 
 
 # Default name of configuration file.  Files with other names may be read.
@@ -558,13 +510,105 @@ def db_colnames(tbl_hdrs):
 		colnames.append(dquote(hdr))
 	return colnames
 
+def isint(v):
+	if v is None or (type(v) is str and v.strip() == ''):
+		return None
+	if type(v) == int:
+		return True
+	if type(v) == float:
+		return False
+	try:
+		int(v)
+		return True
+	except ValueError:
+		return False
+
 def isfloat(v):
+	if v is None or (type(v) is str and v.strip() == ''):
+		return None
 	try:
 		float(v)
 		return True
 	except ValueError:
 		return False
 
+def dt_type(v):
+	# Type of date/time: timestamp, date, time, or None
+	if v is None or (type(v) is str and v.strip() == ''):
+		return None
+	t = None
+	try:
+		t = dateparser.isoparse(v)
+	except:
+		try:
+			t = dateparser.parse(v, ignoretz=True)
+		except:
+			pass
+	if t is None:
+		return None
+	if t.time() == datetime.time(0,0):
+		return "date"
+	else:
+		return "timestamp"
+
+def data_type(v):
+	# Characterizes the value v as one of a simple set of data types.
+	# Returns "timestamp", "date", "int", "float", or "string"
+	if v is None or (type(v) is str and v == ''):
+		return None
+	if isint(v):
+		return "int"
+	if isfloat(v):
+		return "float"
+	dt = dt_type(v)
+	if dt is not None:
+		return dt
+	return "string"
+
+def data_type_cast_fn(data_type_str):
+	if data_type_str == "string":
+		return str
+	elif data_type_str == "date":
+		return datetime.date
+	elif data_type_str == "timestamp":
+		return datetime.timestamp
+	elif data_type_str == "int":
+		return int
+	elif data_type_str == "float":
+		return float
+
+def common_data_type(values):
+	# Returns a data type common to all the values in the list.
+	# This is "string" unlees all types are the same.
+	# Null (None) values are ignored.  If all values are null, return "string".
+	val2 = [v for v in values if v is not None and not (type(v) is str and v.strip() == '')]
+	if len(val2) == 0:
+		return "string"
+	else:
+		types = [data_type(v) for v in val2]
+		if len(set(types)) == 1:
+			return types[0]
+		else:
+			return "string"
+
+def set_data_types(headers, rows, data_type_list):
+	return_queue = queue.Queue()
+	def eval_columns(headers, rows, return_queue):
+		coltypes = []
+		for i, colname in enumerate(headers):
+			datavals = [row[i] for row in rows]
+			non_null = [d for d in datavals if d is not None and not (type(d) is str and d.strip() == '')]
+			nullcount = len(datavals) - len(non_null)
+			uniquevals = len(set(non_null))
+			coltypes.append((colname, common_data_type(datavals), nullcount, uniquevals))
+		return_queue.put(coltypes)
+	t = threading.Thread(target=eval_columns, args=(headers, rows, return_queue))
+	t.start()
+	return (t, return_queue)
+
+# Translations to SQLite type affinity names
+sqlite_type_x = {'int': 'INTEGER', 'float': 'REAL', 'string': 'TEXT', 'timestamp': 'TEXT', 'date': 'TEXT'}
+
 def center_window(win):
 	win.update_idletasks()
 	m = re.match(r"(\d+)x(\d+)\+(-?\d+)\+(-?\d+)", win.geometry())
@@ -577,6 +621,11 @@ def center_window(win):
 		ypos = (sht/2) - (wht/2)
 		win.geometry("%dx%d+%d+%d" % (wwd, wht, xpos, ypos))
 
+def raise_window(win):
+	win.attributes('-topmost', 1)
+	win.attributes('-topmost', 0)
+
+
 
 class MapUI(object):
 	def __init__(self, src_name, message, lat_col, lon_col, crs=4326, sheet=None,
@@ -593,7 +642,6 @@ class MapUI(object):
 		else:
 			# src_name is a filename, either CSV or spreadsheet
 			fn, ext = os.path.splitext(src_name)
-			print("data source extension = %s" % ext)
 			if ext.lower() == ".csv":
 				try:
 					headers, rows = file_data(src_name)
@@ -637,6 +685,8 @@ class MapUI(object):
 		self.max_lat = None
 		self.min_lon = None
 		self.max_lon = None
+		# List of PlotDialog objects, so they can have data pushed or be deleted.
+		self.plot_list = []
 		# Database connection is set in 'add_data()'; variables are initialized here
 		self.dbtmpdir = None
 		self.dbname = None
@@ -795,8 +845,12 @@ class MapUI(object):
 					new_marker = self.map_widget.set_marker(lat_val, lon_val, icon=self.sel_marker_icon)
 					new_markers.append(new_marker)
 			for m in self.sel_map_markers:
-				self.map_widget.delete(m)
+				m.delete()
 			self.sel_map_markers = new_markers
+		else:
+			for m in self.sel_map_markers:
+				m.delete()
+		self.update_plot_data()
 		self.set_status()
 	def set_sel_marker(self, symbol, color):
 		select_marker = tk.BitmapImage(data=icon_xbm[symbol], foreground=color)
@@ -879,7 +933,12 @@ class MapUI(object):
 					self.loc_map_markers.append(mkr)
 			else:
 				self.missing_latlon += 1
+		self.update_plot_data()
 	def add_data(self, rows, headers, lat_col, lon_col, label_col, symbol_col, color_col):
+		# Launch separate process to determine data types
+		self.data_types = []
+		(dt_thread, dt_queue) = set_data_types(headers, rows, self.data_types)
+		# Re-set all data-specific variables and widgets
 		self.lat_col = lat_col
 		self.lon_col = lon_col
 		self.src_lat_col = lat_col
@@ -969,6 +1028,9 @@ class MapUI(object):
 		cur.close()
 		# Initial value for user-entered WHERE clause
 		self.whereclause = ""
+		# Save data types for use in column selection for plotting
+		dt_thread.join()
+		self.data_types = dt_queue.get(block=True)
 		# Return frame and data table
 		return tframe, tdata
 	def remove_data(self):
@@ -977,6 +1039,7 @@ class MapUI(object):
 		while len(self.loc_map_markers) > 0:
 			self.loc_map_markers.pop().delete()
 		self.map_widget.delete_all_marker()
+		self.close_all_plots()
 		self.tableframe.destroy()
 		self.tbl.destroy()
 	def set_tbl_selectmode(self):
@@ -1023,15 +1086,6 @@ class MapUI(object):
 			self.replace_data(rows, headers, lat_col, lon_col, id_col, sym_col, col_col)
 			if desc is not None and desc != '':
 				self.msg_label['text'] = desc
-	#def first_data_file(self):
-	#	dfd = DataFileDialog()
-	#	fn, id_col, lat_col, lon_col, crs, sym_col, col_col, title = dfd.get_datafile()
-	#	if fn is None or fn == '':
-	#		self.cancel()
-	#	else:
-	#		self.crs = crs
-	#		headers, rows = file_data(fn)
-	#		self.tableframe, self.tbl = self.add_data(rows, headers, lat_col, lon_col, id_col, sym_col, col_col)
 	def zoom_full(self):
 		self.map_widget.fit_bounding_box((self.max_lat, self.min_lon), (self.min_lat, self.max_lon))
 	def zoom_selected(self):
@@ -1061,6 +1115,7 @@ class MapUI(object):
 			self.map_widget.delete(m)
 		self.tbl.selection_remove(*self.tbl.selection())
 		self.sel_map_markers = []
+		self.update_plot_data()
 		self.set_status()
 	def change_basemap(self, *args):
 		new_map = self.basemap_var.get()
@@ -1091,6 +1146,7 @@ class MapUI(object):
 					new_marker = self.map_widget.set_marker(lat, lon, icon=self.sel_marker_icon)
 					if not new_marker in self.sel_map_markers:
 						self.sel_map_markers.append(new_marker)
+		self.update_plot_data()
 		self.set_status()
 	def set_status(self):
 		statusmsg = "    %d rows" % self.table_row_count
@@ -1101,6 +1157,45 @@ class MapUI(object):
 		if self.multiselect_var.get() == "1":
 			statusmsg = statusmsg + "  |  Ctrl-click to select multiple rows"
 		self.tblframe.statusbar.config(text = statusmsg)
+
+	def get_all_data(self, column_list):
+		# Plotting support.  Return all data for the specified columns as a list of column-oriented lists.
+		res = []
+		for c in column_list:
+			i = self.headers.index(c)
+			res.append([row[i] for row in self.rows])
+		return res
+	def get_sel_data(self, column_list):
+		# Plotting support.  Return data from selected rows for the specified columns, as a list of lists.
+		res = [[] for _ in column_list]
+		indices = [self.headers.index(c) for c in column_list]
+		for sel_row in self.tbl.selection():
+			datarow = self.tbl.item(sel_row)["values"]
+			for i, index in enumerate(indices):
+				res[i].append(datarow[index])
+		return res
+	def update_plot_data(self, all_data=False):
+		for plot in self.plot_list:
+			if all_data or plot.sel_only_var.get() == "1":
+				plot.q_redraw()
+	def remove_plot(self, plot_obj):
+		# For use by the plot 'do_close()' method.
+		try:
+			self.plot_list.remove(plot_obj)
+		except:
+			pass
+	def close_plot(self, plot_obj):
+		try:
+			plot_obj.do_close()
+			self.remove_plot()
+		except:
+			pass
+	def close_all_plots(self):
+		while len(self.plot_list) > 0:
+			self.plot_list[0].do_close()
+			# The callback will remove the plot.
+		self.plot_list = []
+
 	def change_crs(self):
 		crsdlg = NewCrsDialog(self.crs)
 		new_crs = crsdlg.get_crs()
@@ -1187,11 +1282,13 @@ class MapUI(object):
 		tbl_menu = tk.Menu(mnu, tearoff=0)
 		map_menu = tk.Menu(mnu, tearoff=0)
 		sel_menu = tk.Menu(mnu, tearoff=0)
+		plot_menu = tk.Menu(mnu, tearoff=0)
 		help_menu = tk.Menu(mnu, tearoff=0)
 		mnu.add_cascade(label="File", menu=file_menu, underline=0)
 		mnu.add_cascade(label="Table", menu=tbl_menu, underline=0)
 		mnu.add_cascade(label="Map", menu=map_menu, underline=0)
 		mnu.add_cascade(label="Selections", menu=sel_menu, underline=0)
+		mnu.add_cascade(label="Plot", menu=plot_menu, underline=0)
 		mnu.add_cascade(label="Help", menu=help_menu, underline=0)
 		def save_table():
 			if table_object.selection():
@@ -1309,6 +1406,11 @@ class MapUI(object):
 				f.write("label_size=%s\n" % label_size)
 				f.write("label_bold=%s\n" % ('No' if not label_bold else 'Yes'))
 				f.write("label_position=%s\n" % label_position)
+		def show_data_types():
+			dlg = MsgDialog("Data Types", "Data types, data completeness, and number of unique\nnon-missing values for columns of the data table:")
+			tframe, tdata = treeview_table(dlg.content_frame, self.data_types, ["Column", "Type", "Missing", "Unique"], "browse")
+			tframe.grid(row=0, column=0, sticky=tk.NSEW)
+			dlg.show()
 		def run_query():
 			dlg = QueryDialog(self.headers, self.db, self.whereclause)
 			whereclause = dlg.get_where()
@@ -1343,6 +1445,11 @@ class MapUI(object):
 			self.tbl.selection_set(tuple(new_selections))
 			self.mark_map(None)
 			self.set_status()
+		def new_plot():
+			dlg = PlotDialog(self, self.data_types)
+			self.plot_list.append(dlg)
+			dlg.show
+
 		def online_help():
 			webbrowser.open("https://mapdata.osdn.io", new=2, autoraise=True)
 		def show_config_files():
@@ -1376,6 +1483,7 @@ Copyright %s, R Dreas Nielsen
 		file_menu.add_command(label="Quit", command = self.cancel, underline=0)
 		tbl_menu.add_command(label="Un-select all", command = self.unselect_map, underline=0)
 		tbl_menu.add_command(label="Export selected", command = save_table, underline=1)
+		tbl_menu.add_command(label="Data types", command = show_data_types, underline=5)
 		map_menu.add_command(label="Change marker", command = change_marker, underline=7)
 		map_menu.add_command(label="Zoom selected", command = self.zoom_selected, underline=5)
 		map_menu.add_command(label="Zoom full", command = self.zoom_full, underline=5)
@@ -1386,6 +1494,8 @@ Copyright %s, R Dreas Nielsen
 		sel_menu.add_command(label="Invert", command = invert_selections, underline=0)
 		sel_menu.add_command(label="Un-select all", command = self.unselect_map, underline=0)
 		sel_menu.add_command(label="Set by query", command = run_query, underline=7)
+		plot_menu.add_command(label="New", command = new_plot, underline=0)
+		plot_menu.add_command(label="Close all", command = self.close_all_plots, underline=0)
 		help_menu.add_command(label="Online help", command = online_help, underline=7)
 		help_menu.add_command(label="Config files", command = show_config_files, underline=0)
 		help_menu.add_command(label="About", command = show_about, underline=0)
@@ -1749,10 +1859,11 @@ class ImportSpreadsheetDialog(object):
 		def w1_next():
 			# Open spreadsheet, get sheet names
 			fn, ext = os.path.splitext(self.fn_var.get())
+			ext = ext.lower()
 			try:
-				if ext.lower() == '.ods':
+				if ext == '.ods':
 					sso = OdsFile()
-				elif ext.lower() == '.xlsx':
+				elif ext == '.xlsx':
 					sso = XlsxFile()
 				else:
 					sso = XlsFile()
@@ -1762,10 +1873,17 @@ class ImportSpreadsheetDialog(object):
 				sso.open(self.fn_var.get())
 				self.sheet_list = sso.sheetnames()
 				self.sheet_sel["values"] = self.sheet_list
-				try:
-					sso.close()
-				except:
-					pass
+				if ext in ('.ods', '.xlsx'):
+					try:
+						sso.close()
+					except:
+						pass
+				else:
+					try:
+						sso.release_resources()
+						del sso
+					except:
+						pass
 				wiz2_frame.lift()
 
 		w1btn_frame = tk.Frame(wiz1_frame, borderwidth=3, relief=tk.RIDGE)
@@ -2525,9 +2643,366 @@ class QueryDialog(object):
 			return None
 
 
-def make_top(win):
-	win.attributes('-topmost', 1)
-	win.attributes('-topmost', 0)
+class PlotDialog(object):
+	def __init__(self, parent, column_specs):
+		self.parent = parent
+		self.column_specs = column_specs
+		self.dataset = None
+		self.data_labels = None
+		self.plot_data = None
+		self.plot_data_labels = None
+		self.dlg = tk.Toplevel()
+		self.dlg.title("Plot")
+		self.dlg.columnconfigure(0, weight=1)
+
+		# Message
+		prompt_frame = tk.Frame(self.dlg)
+		prompt_frame.grid(row=0, column=0, sticky=tk.NSEW, pady=(3,3))
+		prompt_frame.columnconfigure(0, weight=1)
+		msg_lbl = ttk.Label(prompt_frame, width=70, text="Select the type of plot, columns for X and Y data, and whether to show all data or only selected data.")
+		msg_lbl.grid(row=0, column=0, sticky=tk.W, padx=(6,6), pady=(3,3))
+		def wrap_msg(event):
+			msg_lbl.configure(wraplength=event.width - 5)
+		msg_lbl.bind("<Configure>", wrap_msg)
+
+		# Controls
+		ctrl_frame = tk.Frame(self.dlg)
+		ctrl_frame.grid(row=1, column=0, sticky=tk.N+tk.EW)
+
+		self.type_var = tk.StringVar(ctrl_frame, "")
+		type_lbl = ttk.Label(ctrl_frame, text="Plot type:")
+		type_lbl.grid(row=0, column=0, sticky=tk.E, padx=(6,3), pady=(3,3))
+		self.type_sel = ttk.Combobox(ctrl_frame, state="readonly", textvariable=self.type_var, width=20,
+				values=["Box plot", "Category counts", "Line plot", "Scatter plot", "Value counts",  "Y range plot"])
+		self.type_sel.grid(row=0, column=1, sticky=tk.W, padx=(3,6), pady=(3,3))
+		self.type_sel.bind("<<ComboboxSelected>>", self.set_xy)
+
+		self.sel_only_var = tk.StringVar(ctrl_frame, "0")
+		self.sel_only_ck = ttk.Checkbutton(ctrl_frame, text="Selected data only", command=self.q_redraw, variable=self.sel_only_var,
+				onvalue="1", offvalue="0")
+		self.sel_only_ck.grid(row=1, column=0, columnspan=2, sticky=tk.W, padx=(6,6), pady=(3,3))
+
+		self.x_var = tk.StringVar(ctrl_frame, "")
+		x_lbl = ttk.Label(ctrl_frame, text="X column:")
+		x_lbl.grid(row=0, column=2, sticky=tk.E, padx=(6,3), pady=(3,3))
+		self.x_sel = ttk.Combobox(ctrl_frame, state="disabled", textvariable=self.x_var, width=20)
+		self.x_sel.grid(row=0, column=3, sticky=tk.W, padx=(3,6), pady=(3,3))
+		self.x_sel.bind("<<ComboboxSelected>>", self.q_redraw)
+
+		self.y_var = tk.StringVar(ctrl_frame, "")
+		y_lbl = ttk.Label(ctrl_frame, text="Y column:")
+		y_lbl.grid(row=1, column=2, sticky=tk.E, padx=(6,3), pady=(3,3))
+		self.y_sel = ttk.Combobox(ctrl_frame, state="disabled", textvariable=self.y_var, width=20)
+		self.y_sel.grid(row=1, column=3, sticky=tk.W, padx=(3,6), pady=(3,3))
+		self.y_sel.bind("<<ComboboxSelected>>", self.q_redraw)
+
+		self.xlog_var = tk.StringVar(ctrl_frame, "0")
+		self.xlog_ck = ttk.Checkbutton(ctrl_frame, text="Log X", state="disabled", command=self.q_redraw, variable=self.xlog_var,
+				onvalue="1", offvalue="0")
+		self.xlog_ck.grid(row=0, column=4, sticky=tk.W, padx=(6,6), pady=(3,3))
+
+		self.ylog_var = tk.StringVar(ctrl_frame, "0")
+		self.ylog_ck = ttk.Checkbutton(ctrl_frame, text="Log Y", state="disabled", command=self.q_redraw, variable=self.ylog_var,
+				onvalue="1", offvalue="0")
+		self.ylog_ck.grid(row=1, column=4, sticky=tk.W, padx=(6,6), pady=(3,3))
+
+		# Plot
+		self.content_frame = tk.Frame(self.dlg, borderwidth=3, relief=tk.RIDGE)
+		self.content_frame.grid(row=2, column=0, sticky=tk.NSEW)
+		self.dlg.rowconfigure(2, weight=1)
+		self.dlg.columnconfigure(0, weight=1)
+		self.content_frame.rowconfigure(0, weight=1)
+		self.content_frame.columnconfigure(0, weight=1)
+		self.plotfig = Figure(dpi=100)
+		self.plotfig.set_figheight(5)
+		self.plotfig_canvas = FigureCanvasTkAgg(self.plotfig, self.content_frame)
+		self.plot_nav = NavigationToolbar2Tk(self.plotfig_canvas, self.content_frame)
+		self.plot_axes = self.plotfig.add_subplot(111)
+		self.plotfig_canvas.get_tk_widget().pack(side=tk.TOP, fill=tk.BOTH, expand=1)
+		self.plot_nav.update()
+
+		# Buttons
+		btn_frame = tk.Frame(self.dlg, borderwidth=3, relief=tk.RIDGE)
+		btn_frame.columnconfigure(0, weight=1)
+		btn_frame.grid(row=3, column=0, sticky=tk.EW, pady=(3,3))
+		btn_frame.columnconfigure(0, weight=0)
+		btn_frame.columnconfigure(1, weight=0)
+		btn_frame.columnconfigure(2, weight=0)
+		btn_frame.columnconfigure(3, weight=1)
+		self.canceled = False
+		self.help_btn = ttk.Button(btn_frame, text="Help", command=self.do_help)
+		self.help_btn.grid(row=0, column=0, sticky=tk.W, padx=(6,3))
+		self.data_btn = ttk.Button(btn_frame, text="Source Data", state="disabled", command=self.show_data)
+		self.data_btn.grid(row=0, column=1, sticky=tk.W, padx=(3,3))
+		self.plot_data_btn = ttk.Button(btn_frame, text="Plot Data", state="disabled", command=self.show_plot_data)
+		self.plot_data_btn.grid(row=0, column=2, sticky=tk.W, padx=(3,6))
+		close_btn = ttk.Button(btn_frame, text="Close", command=self.do_close)
+		close_btn.grid(row=0, column=3, sticky=tk.E, padx=(6,6))
+		self.dlg.bind("<Escape>", self.do_close)
+		center_window(self.dlg)
+		raise_window(self.dlg)
+
+	def do_help(self):
+		webbrowser.open("https://mapdata.osdn.io/dialogs.html#plot-dialog", new=2, autoraise=True)
+
+	def show_data(self):
+		# Show data that have been collected for plotting, but not summarized as needed for a particular plot type.
+		if self.dataset is not None:
+			dlg = MsgDialog("Source Data", "Original data:")
+			variables = len(self.dataset)
+			rowwise_data = []
+			for i in range(len(self.dataset[0])):
+				row = []
+				for j in range(variables):
+					row.append(self.dataset[j][i])
+				rowwise_data.append(row)
+			tframe, tdata = treeview_table(dlg.content_frame, rowwise_data, self.data_labels)
+			tframe.grid(row=0, column=0, sticky=tk.NSEW)
+			dlg.show()
+
+	def show_plot_data(self):
+		# Show data that have been collected for plotting, but not summarized as needed for a particular plot type.
+		if self.plot_data is not None:
+			dlg = MsgDialog("Data for Plotting", "Data to be plotted:")
+			variables = len(self.plot_data)
+			rowwise_data = []
+			max_data_len = max([len(self.plot_data[i]) for i in range(variables)])
+			for i in range(max_data_len):
+				row = []
+				for j in range(variables):
+					try:
+						# Boxplot data are not necessarily a full matrix
+						row.append(self.plot_data[j][i])
+					except:
+						row.append(None)
+				rowwise_data.append(row)
+			tframe, tdata = treeview_table(dlg.content_frame, rowwise_data, self.plot_data_labels)
+			tframe.grid(row=0, column=0, sticky=tk.NSEW)
+			dlg.show()
+
+	def set_xy(self, *args):
+		# Enable X and Y value selection, and set values based on plot type and column types.
+		# Conditionally (re)draw the plot.
+		self.plotfig.clear()
+		self.plot_axes = self.plotfig.add_subplot(111)
+		self.plotfig_canvas.draw()
+		self.dataset = None
+		self.data_labels = None
+		self.plot_data = None
+		self.plot_data_labels = None
+		self.data_btn["state"] = "disabled"
+		self.plot_data_btn["state"] = "disabled"
+		categ_columns = [c[0] for c in self.column_specs if c[1] == "string"]
+		quant_columns = [c[0] for c in self.column_specs if c[1] != "string"]
+		plot_type = self.type_var.get()
+		self.x_var.set('')
+		self.y_var.set('')
+		if plot_type == "Category counts":
+			self.x_sel["values"] = categ_columns
+			self.xlog_ck["state"] = "disabled"
+			self.x_sel["state"] = "readonly"
+			self.y_sel["state"] = "disabled"
+			self.ylog_ck["state"] = "disabled"
+		elif plot_type == "Value counts":
+			self.x_sel["values"] = quant_columns
+			self.xlog_ck["state"] = "normal"
+			self.x_sel["state"] = "readonly"
+			self.y_sel["state"] = "disabled"
+			self.ylog_ck["state"] = "disabled"
+		elif plot_type == "Box plot":
+			self.x_sel["values"] = categ_columns
+			self.xlog_ck["state"] = "disabled"
+			self.y_sel["values"] = quant_columns
+			self.x_sel["state"] = "readonly"
+			self.y_sel["state"] = "readonly"
+			self.ylog_ck["state"] = "normal"
+		else:
+			self.x_sel["values"] = quant_columns
+			self.xlog_ck["state"] = "normal"
+			self.y_sel["values"] = quant_columns
+			self.x_sel["state"] = "readonly"
+			self.y_sel["state"] = "readonly"
+			self.ylog_ck["state"] = "normal"
+
+	def q_redraw(self, *args):
+		# Conditionally (re)draw the plot.
+		plot_type = self.type_var.get()
+		can_redraw = (plot_type in ("Category counts", "Value counts") and self.x_var.get() != '') \
+				or (plot_type in ("Scatter plot", "Line plot", "Box plot", "Y range plot") and self.x_var.get() != '' and self.y_var.get() != '')
+		if can_redraw:
+			self.plotfig.clear()
+			self.plot_axes = self.plotfig.add_subplot(111)
+			self.plotfig_canvas.draw()
+			self.get_data()
+			if self.dataset is not None:
+				self.redraw()
+
+	def get_data(self):
+		self.data_btn["state"] = "disabled"
+		self.plot_data_btn["state"] = "disabled"
+		self.dataset = None
+		plot_type = self.type_var.get()
+		column_list = [self.x_var.get()]
+		if self.y_var.get() != '':
+			column_list.append(self.y_var.get())
+		if self.sel_only_var.get() == "1":
+			dataset = self.parent.get_sel_data(column_list)
+		else:
+			dataset = self.parent.get_all_data(column_list)
+		if dataset is None or len(dataset[0]) == 0:
+			self.dataset = None
+			self.data_labels = None
+			self.plot_data = None
+			self.plot_data_labels = None
+			self.data_btn["state"] = "disabled"
+			self.plot_data_btn["state"] = "disabled"
+		else:
+			# Remove missing data
+			column_indexes = range(len(dataset))
+			clean_data = [[] for _ in dataset]
+			for i in range(len(dataset[0])):
+				ok = True
+				for col in column_indexes:
+					if dataset[col][i] is None or dataset[col][i] == '':
+						ok = False
+				if ok:
+					for col in column_indexes:
+						clean_data[col].append(dataset[col][i])
+			dataset = None
+			# Convert quantitative data types
+			if plot_type != "Category counts":
+				x_data_type = [cs[1] for cs in self.column_specs if cs[0] == self.x_var.get()][0]
+				cast_fn = data_type_cast_fn(x_data_type)
+				for i in range(len(clean_data[0])):
+					clean_data[0][i] = cast_fn(clean_data[0][i])
+			if self.y_sel["state"] != "disabled" and self.y_var.get() != "" and len(clean_data) > 1:
+				y_data_type = [cs[1] for cs in self.column_specs if cs[0] == self.y_var.get()][0]
+				cast_fn = data_type_cast_fn(y_data_type)
+				for i in range(len(clean_data[1])):
+					clean_data[1][i] = cast_fn(clean_data[1][i])
+			# Log-transform data if specified.
+			if (self.xlog_ck["state"] != "disabled" and self.xlog_var.get() == "1") or (self.ylog_ck["state"] != "disabled" and self.ylog_var.get() == "1" and len(clean_data) > 1):
+				log_data = [[] for _ in clean_data]
+				log_error = False
+				if self.xlog_ck["state"] != "disabled" and self.xlog_var.get() == "1":
+					for i in range(len(clean_data[0])):
+						try:
+							log_data[0].append(math.log10(clean_data[0][i]))
+						except:
+							log_error = True
+							break
+				else:
+					log_data[0] = clean_data[0]
+				if not log_error and self.ylog_ck["state"] != "disabled" and self.ylog_var.get() == "1" and len(clean_data) > 1:
+					for i in range(len(clean_data[1])):
+						try:
+							log_data[1].append(math.log10(clean_data[1][i]))
+						except:
+							log_error = True
+							break
+				else:
+					if len(clean_data) > 1:
+						log_data[1] = clean_data[1]
+				if not log_error:
+					clean_data = log_data
+				log_data = None
+			self.dataset = clean_data
+			if self.y_var.get() != '':
+				self.data_labels = [self.x_var.get(), self.y_var.get()]
+			else:
+				self.data_labels = [self.x_var.get()]
+			self.data_btn["state"] = "normal"
+			# Summarize and sort the data as needed for each type of plot.
+			if plot_type == "Category counts":
+				# Count of values for each X, ordered by X
+				counter = collections.Counter(self.dataset[0])
+				x_vals = list(counter.keys())
+				x_vals.sort()
+				x_counts = [counter[k] for k in x_vals]
+				self.plot_data = [x_vals, x_counts]
+				self.plot_data_labels = [self.x_var.get(), "Count"]
+			elif plot_type == "Box plot":
+				# A list of Y values for each X value
+				x_vals = list(set(self.dataset[0]))
+				ds = list(zip(self.dataset[0], self.dataset[1]))
+				plot_data = []
+				for x in x_vals:
+					plot_data.append([d[1] for d in ds if d[0] == x])
+				self.plot_data = plot_data
+				self.plot_data_labels = x_vals
+			elif plot_type == "Y range plot":
+				# Min and max Y for each X
+				x_vals = list(set(self.dataset[0]))
+				x_vals.sort()
+				y_vals = [[None, None]] * len(x_vals)
+				plotdata = dict(zip(x_vals, y_vals))
+				for i in range(len(self.dataset[0])):
+					x = self.dataset[0][i]
+					y = self.dataset[1][i]
+					y_vals = plotdata[x]
+					if y_vals[0] is None or y < y_vals[0]:
+						plotdata[x][0] = y
+					if y_vals[1] is None or y > y_vals[1]:
+						plotdata[x][1] = y
+				y1 = [plotdata[x][0] for x in x_vals]
+				y2 = [plotdata[x][1] for x in x_vals]
+				self.plot_data = [x_vals, y1, y2]
+				self.plot_data_labels = [self.x_var.get(), self.y_var.get() + " min", self.y_var.get() + " max"]
+			elif plot_type == "Line plot":
+				# Sort by X
+				ds = list(zip(self.dataset[0], self.dataset[1]))
+				ds.sort()
+				ds2 = list(zip(*ds))
+				self.plot_data = [list(ds2[0]), list(ds2[1])]
+				self.plot_data_labels = self.data_labels
+			elif plot_type in ("Value counts", "Scatter plot", "Y range plot"):
+				# No special preparation
+				self.plot_data = self.dataset
+				self.plot_data_labels = self.data_labels
+			self.plot_data_btn["state"] = "normal"
+
+	def redraw(self):
+		#self.plotfig.clear()
+		#self.plot_axes = self.plotfig.add_subplot(111)
+		#self.plotfig_canvas.draw()
+		plot_type = self.type_var.get()
+		if self.plot_data is not None and len(self.plot_data[0]) > 0:
+			if plot_type == "Category counts":
+				self.plot_axes.bar(self.plot_data[0], self.plot_data[1])
+				self.plot_axes.set_xlabel(self.x_var.get())
+				self.plot_axes.set_ylabel("Counts")
+			elif plot_type == "Value counts":
+				self.plot_axes.hist(self.plot_data[0])
+				self.plot_axes.set_xlabel(self.x_var.get())
+				self.plot_axes.set_ylabel("Counts")
+			elif plot_type == "Scatter plot":
+				self.plot_axes.scatter(self.plot_data[0], self.plot_data[1])
+				self.plot_axes.set_xlabel(self.x_var.get())
+				self.plot_axes.set_ylabel(self.y_var.get())
+			elif plot_type == "Line plot":
+				self.plot_axes.plot(self.plot_data[0], self.plot_data[1])
+				self.plot_axes.set_xlabel(self.x_var.get())
+				self.plot_axes.set_ylabel(self.y_var.get())
+			elif plot_type == "Y range plot":
+				self.plot_axes.fill_between(self.plot_data[0], self.plot_data[1], self.plot_data[2])
+				self.plot_axes.set_xlabel(self.x_var.get())
+				self.plot_axes.set_ylabel(self.y_var.get())
+			elif plot_type == "Box plot":
+				self.plot_axes.boxplot(self.plot_data, labels=self.plot_data_labels)
+				self.plot_axes.set_xlabel(self.x_var.get())
+				self.plot_axes.set_ylabel(self.y_var.get())
+			self.plotfig_canvas.draw()
+			self.plot_nav.update()
+
+	def do_close(self, *args):
+		self.parent.remove_plot(self)
+		self.dlg.destroy()
+	def show(self):
+		self.dlg.update_idle_tasks()
+		self.dlg.minsize(width=500, height=500)
+		self.dlg.wait_window(self.dlg)
+
+
 
 class MsgDialog(object):
 	#def __init__(self, title, message, width=400, height=400):
@@ -2538,9 +3013,11 @@ class MsgDialog(object):
 		prompt_frame.grid(row=0, column=0, sticky=tk.NSEW, pady=(3,3))
 		msg_lbl = ttk.Label(prompt_frame, text=message)
 		msg_lbl.grid(row=0, column=0, padx=(6,6), pady=(3,3))
+		self.content_frame = tk.Frame(self.dlg)
+		self.content_frame.grid(row=1, column=0, sticky=tk.NSEW)
 		btn_frame = tk.Frame(self.dlg, borderwidth=3, relief=tk.RIDGE)
 		btn_frame.columnconfigure(0, weight=1)
-		btn_frame.grid(row=1, column=0, sticky=tk.EW, pady=(3,3))
+		btn_frame.grid(row=2, column=0, sticky=tk.EW, pady=(3,3))
 		btn_frame.columnconfigure(0, weight=1)
 		# Buttons
 		self.canceled = False
@@ -2553,7 +3030,7 @@ class MsgDialog(object):
 	def show(self):
 		self.dlg.grab_set()
 		center_window(self.dlg)
-		make_top(self.dlg)
+		raise_window(self.dlg)
 		self.dlg.resizable(False, False)
 		self.dlg.wait_window(self.dlg)
 
@@ -2619,7 +3096,7 @@ class SelDataSrcDialog(object):
 	def select(self):
 		self.dlg.grab_set()
 		center_window(self.dlg)
-		make_top(self.dlg)
+		raise_window(self.dlg)
 		self.dlg.resizable(False, False)
 		self.dlg.wait_window(self.dlg)
 		return self.rv
@@ -3025,7 +3502,7 @@ class XlsFile(object):
 		self.wbk = xlrd.open_workbook(filename, encoding_override=self.encoding)
 		self.datemode = self.wbk.datemode
 	def sheetnames(self):
-		return self.wbk.sheets()
+		return self.wbk.sheet_names()
 	def sheet_named(self, sheetname):
 		# Return the sheet with the matching name.  If the name is actually an integer,
 		# return that sheet number.
@@ -3185,7 +3662,8 @@ class XlsxFile(object):
 def xls_data(filename, sheetname, junk_header_rows, encoding=None):
 	# Returns the data from the specified worksheet as a list of headers and a list of lists of rows.
 	root, ext = os.path.splitext(filename)
-	if ext == "xls":
+	ext = ext.lower()
+	if ext == ".xls":
 		wbk = XlsFile()
 	else:
 		wbk = XlsxFile()

{mapdata-1.10.1 → mapdata-2.0.2/mapdata.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mapdata
-Version: 1.10.1
+Version: 2.0.2
 Summary: An interactive map and table explorer for geographic coordinates in a CSV file
 Home-page: https://osdn.net/project/mapdata/
 Author: Dreas Nielsen
@@ -27,6 +27,7 @@ Requires: pyproj
 Requires: odfpy
 Requires: openpyxl
 Requires: xlrd
+Requires: matplotlib
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
@@ -63,6 +64,12 @@ export the map to an image file, and quit.
 
 Selected rows in the data table can be exported to a CSV or spreadsheet file.
 
+Data can also be displayed in several different types of plots: box plots, scatter
+plots, line charts, and counts of categorical and quantitative variables.  Plots
+can use either all data or only data values that are selected in the map and
+table.  Plots have a live connection to the data table, so when selections are
+changed the plots are automatically updated.
+
 
 Complete documentation is at [https://mapdata.osdn.io](https://mapdata.osdn.io).
 

{mapdata-1.10.1 → mapdata-2.0.2}/setup.py

@@ -5,14 +5,14 @@ with io.open('README.md', encoding='utf-8') as f:
 	long_description = f.read()
 
 setuptools.setup(name='mapdata',
-	version='1.10.1',
+	version='2.0.2',
 	description="An interactive map and table explorer for geographic coordinates in a CSV file",
 	author='Dreas Nielsen',
 	author_email='dreas.nielsen@gmail.com',
     url='https://osdn.net/project/mapdata/',
 	scripts=['mapdata/mapdata.py'],
     license='GPL',
-	requires=['tkintermapview', 'pyproj', 'odfpy', 'openpyxl', 'xlrd'],
+	requires=['tkintermapview', 'pyproj', 'odfpy', 'openpyxl', 'xlrd', 'matplotlib'],
 	python_requires = '>=3.8',
 	classifiers=[
 		'Development Status :: 5 - Production/Stable',