initial commit

.gitignore

@@ -0,0 +1,106 @@
+.DS_Store
+
+# Created by https://www.gitignore.io/api/python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+.pytest_cache/
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule.*
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+
+# End of https://www.gitignore.io/api/python

README.md

@@ -0,0 +1,59 @@
+# Simple Visual Geocoder
+
+[Download from GitHub](https://github.com/jsoma/simple-visual-geocoder/releases/download/v0.1/SimpleVisualGeocoder.zip)
+
+## Batch geocode CSV files _on your own machine_ using the Census API
+
+Geocoding is a pain in the neck. If you're just looking at US addresses, though, Simple Visual Geocoder is here to help! **Latitude and longitude are on the way.**
+
+![](screenshots/main.png)
+
+Simple Visual Geocoder takes in CSV files and geocodes them with the [Census Bureau's Batch Geocoding service](https://www.documentcloud.org/documents/3894452-Census-Geocoding-Services-API.html) - **all without knowing Python or using the command line!**
+
+It's more or less a very thin later on top of the LA Times' [Census Batch Geocoder](https://github.com/datadesk/python-censusbatchgeocoder), with the addition of a few simple tools to help you break out street addresses and city names.
+
+As a fun bonus, you don't need to upload your data into 🌪 THE CLOUD 🌪.
+
+## Using Simple Visual Geocoder
+
+### Downloading
+
+You can download the latest release [from GitHub](https://github.com/jsoma/simple-visual-geocoder/releases/download/v0.1/SimpleVisualGeocoder.zip).
+
+### Simple How-To
+
+1. Click `Browse...` to select your file
+2. Pick your columns that contain address, city, state and zipcode (state and zipcode are optional)
+3. Click `Geocode` button, pick a destination for your new geocoded data
+4. Wait and wait and wait (don't worry, it isn't frozen!)
+5. A brand-new CSV file shows up, full of latitudes and longitudes!
+6. 🎉🎉🎉
+
+### Cleaning your data with "Adjustments"
+
+The Census Bureau requires you do split `address`, `city`, `state`, and `zipcode` into separate fields. But what if your addresses aren all in one column and  look like this?
+
+```
+540 Streetsway Avenue, Townsville, NC
+101 Rock and Roll St, Apt 3, Guitar City, NV
+```
+
+Oh no! Do we need to split it apart? Do we need to get rid of that apartment? No! No! **Don't worry, Simple Visual Geocoder is here!** It has built-in data cleaning tools called Adjustments to make splitting long addresses up easy.
+
+When you pick your column for `address` you can add an Adjustment: "Split up the _big long full address_ according to the commas, and only give me the _first section_." That would give us `540 Streetsway Avenue ` and `101 Rock and Roll St`.
+
+You can also pluck out the states from the end by saying "Split it up by commas and give me the _last_ piece." `NC` and `NV`, delivered to your doorstep.
+
+There are options to use this on both commas as well as newlines/linebreaks.
+
+## Troubleshooting
+
+### I think maybe it only works on OS X?
+
+But it shouldn't be tough to make it work on PCs, too.
+
+### Help! I told it to geocode and it froze up!
+
+It didn't freeze, it's just busy geocoding for you! It should finish eventually. Just be patient. Very, very patient.
+
+_At some point it would be nice to implement threads so that this doesn't happen._

app/app.py

@@ -0,0 +1,223 @@
+from  parsedatetime.pdt_locales import (
+    de_DE, en_AU, en_US,
+    es, nl_NL, pt_BR,
+    ru_RU, fr_FR)
+
+from PyQt5.QtWidgets import (QMainWindow, QTextEdit, 
+    QAction, QFileDialog, QApplication, QWidget, QLabel, 
+    QComboBox, QApplication, QHBoxLayout, QVBoxLayout, QPushButton,
+    QTableWidget,QTableWidgetItem, QGridLayout)
+from PyQt5.QtGui import QIcon
+from PyQt5.QtCore import Qt
+import sys
+import os
+import pandas as pd
+from collections import OrderedDict
+import censusbatchgeocoder
+import traceback
+
+ROW_COUNT = 20
+
+ADJUSTMENTS = OrderedDict()
+ADJUSTMENTS["None"] = lambda x: x
+ADJUSTMENTS["Comma split: first section"] = lambda x: x.split(",")[0]
+ADJUSTMENTS["Comma split: second"] = lambda x: x.split(",")[1]
+ADJUSTMENTS["Comma split: third"] = lambda x: x.split(",")[2]
+ADJUSTMENTS["Comma split: second-to-last"] = lambda x: x.split(",")[-2]
+ADJUSTMENTS["Comma split: last"] = lambda x: x.split(",")[-1]
+ADJUSTMENTS["Newline split: first section"] = lambda x: x.split("\n")[0]
+ADJUSTMENTS["Newline split: second"] = lambda x: x.split("\n")[1]
+ADJUSTMENTS["Newline split: third"] = lambda x: x.split("\n")[2]
+ADJUSTMENTS["Newline split: second-to-last"] = lambda x: x.split("\n")[-2]
+ADJUSTMENTS["Newline split: last"] = lambda x: x.split("\n")[-1]
+
+class VisualCensusGeocoder(QWidget):
+
+    def __init__(self):
+        super().__init__()
+
+        self.filename = None
+
+        self.initUI()
+
+
+    def initUI(self):      
+        vbox = QVBoxLayout()
+
+        # File picker
+
+        file_picker = QPushButton("Browse...")
+        file_picker.clicked.connect(self.showFilePicker)
+
+        row = QHBoxLayout()
+        row.addWidget(file_picker)
+        self.file_label = QLabel("Please select a CSV file to geocode")
+        row.addWidget(self.file_label)
+
+        row.addStretch(1)
+
+        vbox.addLayout(row)
+
+        # Not using .keys() to keep them in order when drawing
+        self.field_names = ['address', 'city', 'state', 'zipcode']
+        self.fields = {
+            'address': { 'title': 'Address', 'column': 0 },
+            'city': { 'title': 'City', 'column': 1 },
+            'state': { 'title': 'State', 'column': 2 },
+            'zipcode': { 'title': 'Zipcode', 'column': 3 }
+        }
+
+        for key in self.field_names:
+            field_selector = QComboBox(self)
+            field_selector.currentIndexChanged.connect(self.comboChanged)
+            self.fields[key]['combo'] = field_selector
+
+            adjustment_selector = QComboBox(self)
+            adjustment_selector.addItems(ADJUSTMENTS.keys())
+            adjustment_selector.currentIndexChanged.connect(self.comboChanged)
+            self.fields[key]['adjustment'] = adjustment_selector
+
+            self.fields[key]['sample'] = QLabel("")
+
+        grid = QGridLayout()
+
+        grid.addWidget(QLabel("<strong>Column Name</strong>"), 0, 1, 1, 2)
+        grid.addWidget(QLabel("<strong>Adjustments</strong>"), 0, 3, 1, 2)
+        grid.addWidget(QLabel("<strong>Column Sample</strong>"), 0, 5, 1, 2)
+
+        for i, key in enumerate(self.field_names):
+            field = self.fields[key]
+            grid.addWidget(QLabel(field['title']), i+1, 0, 1, 1, alignment=Qt.AlignRight)
+            grid.addWidget(field['combo'], i+1, 1, 1, 2)
+            grid.addWidget(field['adjustment'], i+1, 3, 1, 2)
+            grid.addWidget(field['sample'], i+1, 5, 1, 2)
+        vbox.addLayout(grid)
+
+        # Preview
+        vbox.addWidget(QLabel("<strong>API Preview</strong>"))
+
+        self.table = QTableWidget()
+        self.table.setRowCount(ROW_COUNT)
+        self.table.setColumnCount(4)
+        self.table.setHorizontalHeaderLabels(["Address", "City", "State", "ZIP"])
+        self.table.verticalHeader().setVisible(False)
+
+        row = QHBoxLayout()
+        row.addWidget(self.table)
+        vbox.addLayout(row)
+
+        # Geocode button
+        geo_button = QPushButton("Geocode")
+        geo_button.clicked.connect(self.doGeocode)
+
+        row = QHBoxLayout()
+        row.addWidget(geo_button)
+
+        vbox.addLayout(row)
+
+        self.setLayout(vbox)     
+
+        self.setGeometry(300, 300, 750, 500)
+        self.setWindowTitle('Visual Census Geocoder')
+        self.table.setMinimumSectionSize = 150
+        self.table.horizontalHeader().setSectionResizeMode(0, 1)
+        self.table.horizontalHeader().setSectionResizeMode(1, 1)
+        self.table.horizontalHeader().setSectionResizeMode(2, 2)
+        self.table.horizontalHeader().setSectionResizeMode(3, 2)
+        self.show()
+
+    def prepareForGeocoding(self, row):
+        data = {}
+        data['id'] = row.name
+
+        for key in self.field_names:
+            try:
+                data_col_name = self.fields[key]['combo'].currentText()
+                adjustment_name = self.fields[key]['adjustment'].currentText()
+                adjustment = ADJUSTMENTS[adjustment_name]
+                val = adjustment(row[data_col_name])
+
+                data[key] = val
+            except:
+                data[key] = ""
+        return data
+
+    def doGeocode(self):
+        self.pickTargetFilename()
+
+        if self.target_filename:
+            for_geocoding = self.df.fillna("").apply(self.prepareForGeocoding, axis=1)
+            results = censusbatchgeocoder.geocode(for_geocoding)
+            results_df = pd.DataFrame(results)
+            self.df.merge(results_df, 
+                left_index=True, 
+                right_on='id', 
+                suffixes=("","_geo")
+            ).to_csv(self.target_filename)
+            os.system("open -R \"%s\"" % self.target_filename)
+
+    def updateColumn(self, field):
+        colnum = field['column']
+        data_col_name = field['combo'].currentText()
+        adjustment_name = field['adjustment'].currentText()
+
+        for index, row in self.df.head(ROW_COUNT).fillna("").iterrows():
+            try:
+                adjustment = ADJUSTMENTS[adjustment_name]
+                val = adjustment(row[data_col_name])
+                if index == 0:
+                    field['sample'].setText("<small>" + row[data_col_name] + "</small>")
+                self.table.setItem(index, colnum, QTableWidgetItem(val))
+            except:
+                self.table.setItem(index, colnum, QTableWidgetItem(""))
+
+    def comboChanged(self):
+        for key in self.field_names:
+            self.updateColumn(self.fields[key])
+
+    def updateComboBoxes(self):
+        options = ['-'] + list(self.df.columns.values) + ['custom', 'none']
+        for index, key in enumerate(self.field_names):
+            combo = self.fields[key]['combo']
+            combo.clear()
+            combo.addItems(options)
+            self.fields[key]['adjustment'].setCurrentIndex(0)
+
+    def updateTable(self):
+        rows = df.head()
+
+    def pickTargetFilename(self):
+        fname = QFileDialog.getSaveFileName(self, 
+            'Select output filename', 
+            self.filename.replace(".csv", "-geocoded.csv"))
+
+        if fname[0]:
+            self.target_filename = fname[0]
+        else:
+            self.target_filename = None
+
+    def showFilePicker(self):
+        fname = QFileDialog.getOpenFileName(self, 
+            'Select file')
+
+        if fname[0]:
+            self.filename = fname[0]
+            self.df = pd.read_csv(self.filename, dtype='str')
+            self.file_label.setText(self.filename)
+            self.updateComboBoxes()
+
+            # with f:
+            #     data = f.read()
+            #     self.textEdit.setText(data) 
+
+    def onActivated(self, text):
+
+        self.lbl.setText(text)
+        self.lbl.adjustSize()  
+
+
+if __name__ == '__main__':
+
+    app = QApplication(sys.argv)
+    ex = VisualCensusGeocoder()
+    sys.exit(app.exec_())