Export Topic Labels
In [1]:
import os
import pandas as pd
import gspread
from oauth2client.service_account import ServiceAccountCredentials
In [2]:
scope = ['https://spreadsheets.google.com/feeds']
secrets = "/Users/jeriwieringa/Dissertation/dev/code/secrets/dissertation-881847769b13.json"
credentials = ServiceAccountCredentials.from_json_keyfile_name(secrets, scope)
In [3]:
gc = gspread.authorize(credentials)
In [4]:
dts = gc.open('Topic Labels').sheet1
frame = pd.DataFrame(dts.get_all_records())
In [5]:
frame[:10]
Out[5]:
| browser_topic_id | mallet_topic_id | topic_category | topic_label | topic_prevalence_overall | topic_words | |
|---|---|---|---|---|---|---|
| 0 | 1 | 0 | missions | Missions (Canvassing Work) | 0.02981 | book canvasser order canvassing brother week s... |
| 1 | 2 | 1 | nutrition | Nutrition (Recipes) | 0.00927 | cup water bread egg add cream salt flour milk ... |
| 2 | 3 | 2 | scan_errors | Scan Errors (OCR Errors) | 0.03660 | ing tion ment sign ness com ter tions great en... |
| 3 | 4 | 3 | social_commentary | Social Commentary (Suffering and Death from Vi... | 0.03036 | death man blood men like life hand victim poor... |
| 4 | 5 | 4 | spiritual_growth | Spiritual Growth (Christian Life - Perseverance) | 0.02033 | shall lord unto faith thing hope trial christ ... |
| 5 | 6 | 5 | sermons | Sermons (Religious Practice) | 0.10352 | thing know think way man want let doe right go... |
| 6 | 7 | 6 | bible | Bible (Stories from Daniel and Babylonian Capt... | 0.01276 | king daniel babylon jerusalem lord kingdom neb... |
| 7 | 8 | 7 | scan_errors | Scan Errors (OCR Errors 2) | 0.04291 | ing lie review end herald ill tie ile tho good... |
| 8 | 9 | 8 | spiritual_growth | Spiritual Growth (Christian Behavior) | 0.01902 | prayer lord heart spirit blessing let church m... |
| 9 | 10 | 9 | reports_on_the_cause | Reports on the Cause ("Progress of the Cause") | 0.01000 | meeting church brother lord sabbath truth held... |
In [6]:
topic2id = pd.Series(frame.topic_label.values,index=frame.browser_topic_id)
In [7]:
dict_view = {}
for index, value in topic2id.iteritems():
dict_view["{}".format(index)] = "{}".format(value)
In [8]:
import json
In [9]:
print(json.dumps(dict_view, indent=2, sort_keys=True))
{
"1": "Missions (Canvassing Work)",
"10": "Reports on the Cause (\"Progress of the Cause\")",
"100": "Theology (Christ and salvation)",
"101": "Signs of the Times (Astronomy)",
"102": "Conference Proceedings (Discussions)",
"103": "Piety (Testimonies and Letters)",
"104": "Theology (Sabbath Keeping)",
"105": "Education (Educational Theory)",
"106": "Meeting Reports (SDA Institutions)",
"107": "Advertisements (Printing)",
"108": "Health (Sanitariums - West Coast)",
"109": "Advertisements (Subscriptions)",
"11": "Theology (The Soul)",
"110": "Social Commentary (Labor Organization and Disputes)",
"111": "Missions (Prison Ministries)",
"112": "Stories (Moralistic Stories)",
"113": "Piety (Ocean as metaphor for life) ",
"114": "Education (SDA Colleges)",
"115": "Theology (Sin)",
"116": "Stories (Health-related)",
"117": "Reports on the Cause (Field Reports)",
"118": "Eschatology (Parable of Bridegroom and Tarrying Time)",
"119": "Missions (News and Announcements)",
"12": "Stories (Children's)",
"120": "Apologetics (Geology and Evolution)",
"121": "Advertisements (Pacific Press Books)",
"122": "General Interest (Population and Statistics)",
"123": "Nutrition (Grains)",
"124": "Organization (Statistical Summaries)",
"125": "Organization (Place names)",
"126": "Reports on the Cause (History of SDA Work)",
"127": "Bible (New Testament Lessons)",
"128": "Missions",
"129": "Conference Proceedings (Resolutions and Summaries)",
"13": "Spiritual Growth (Christian Virtue - Development)",
"130": "Apologetics (Other Religions)",
"131": "Prophecy (Figures of Revelation)",
"132": "Theology (Sabbath Keeping)",
"133": "Organization (Funds and Figures - Pacific Union)",
"134": "Advertisements (SDA Publications - early)",
"135": "History (Sunday Observance)",
"136": "Education (Teaching Plans)",
"137": "Health (Rest)",
"138": "Church & State (Religious Amendments and National Reform Association)",
"139": "Advertisements",
"14": "Sermons (Salvation Narrative)",
"140": "Education (Sabbath Lessons)",
"141": "Theology (the Fall)",
"142": "Signs of the Times (Crime and Immorality)",
"143": "Missions (South America)",
"144": "Health (Ventilation)",
"145": "Organization (Church Finances)",
"146": "Eschatology (Sanctuary Doctrine)",
"147": "Organization (Funds and Figures - Lake Union)",
"148": "Nature (Animals)",
"149": "Reports on the Cause (Building Projects)",
"15": "Reports on the Cause (News and Field Reports)",
"150": "Social Commentary (Commerce and Money)",
"151": "Obituaries (Death Notices)",
"152": "Obituaries (Death Notices)",
"153": "Theology (Prayer)",
"154": "Church & State (Arguments against Sabbath Laws)",
"155": "Advertisements (Sanitariums)",
"156": "Theology (the Sabbath Question)",
"157": "Advertisements (Books and Literature)",
"158": "Advertisements (Premium Bibles)",
"159": "Signs of the Times (\"Catholic Threat\")",
"16": "Politics (Religious Freedom)",
"160": "Theology (Baptism and Sacraments)",
"161": "Health (Habits)",
"162": "Theology (Seventh-day Sabbath)",
"163": "Organization (Lists of Donors and People)",
"164": "Signs of the Times (War)",
"165": "Stories (Moralistic Story - Family)",
"166": "Stories (Theological)",
"167": "Church & State (Sabbath Laws)",
"168": "Theology (Ten Commandments)",
"169": "Social Commentary (Temperance)",
"17": "Piety (Poetry)",
"170": "Spiritual Growth (Overcoming Temptation and Sin)",
"171": "Eschatology (Events of the Last Days)",
"172": "Spiritual Growth (Calls for Charity)",
"173": "History (History in the Light of Prophecy)",
"174": "Organization (Notices of Meetings and Appointments)",
"175": "Nutrition (Foods and Recipes)",
"176": "Organization (Columbia Union - Ohio - Activity Reports)",
"177": "Missions (Africa)",
"178": "Religious Commentary (Preaching and Ministry)",
"179": "Bible (Quotations)",
"18": "General Interest (News and Notes)",
"180": "Signs of the Times (Global Unrest)",
"181": "Social Commentary (Testimonies and Moral Commentary - largely EGW)",
"182": "General Interest (Natural Disasters)",
"183": "Eschatology (Description of Second Coming)",
"184": "Health (Alcohol and Disease)",
"185": "Health (Dangers of Alcohol)",
"186": "Nature (Flora and Fauna)",
"187": "Advertisements (Life Boat)",
"188": "Health (Regular Medicine)",
"189": "Bible (New Testament - Apostles)",
"19": "Education (Medical Training Programs)",
"190": "Theology (Righteousness by Faith)",
"191": "Bible (Old Testament - Prophets)",
"192": "Bible (Ten Commandments - Quoted)",
"193": "Transportation (Trains)",
"194": "Correspondence (Letters from Children)",
"195": "Nutrition (Food - Meat)",
"196": "Piety (Religious Comfort)",
"197": "Theology (Holy Spirit)",
"198": "Spiritual Growth (Christian Virtue)",
"199": "Missions (Missions Work)",
"2": "Nutrition (Recipes)",
"20": "Advertisements (Transportation)",
"200": "Eschatology (Second Coming)",
"201": "Community News (Indiana)",
"202": "Stories (Religious Stories)",
"203": "Education (Farming and Agriculture)",
"204": "Advertisements (Notices and Appointments)",
"205": "Health (Eyes)",
"206": "Missions (Sabbath School and Home Department)",
"207": "Bible (Parables - Sower)",
"208": "Advertisements (Bible Readers)",
"209": "Education (Crafting Instructions)",
"21": "Organization (Church Organization)",
"210": "Reports on the Cause (\"Progress of the Cause\" - Reports on Local Reception)",
"211": "Church & State (Religion Legislation and the Courts)",
"212": "History (Reformation)",
"213": "Organization (Report of Offerings)",
"214": "Apologetics (Rebuttals and Responses)",
"215": "Religious Commentary (Death)",
"216": "Prophecy (Interpreting Dates and Time)",
"217": "Health (Digestive System)",
"218": "Missions (India)",
"219": "Organization (Financial Report)",
"22": "Politics (Principles of the Republic and their Violation)",
"220": "Advertisements (Periodicals)",
"221": "Missions (Home Missions)",
"222": "Church & State (Religion in Public Education)",
"223": "Bible (Quotations)",
"224": "Community News (Lake Union & Tithe Reports)",
"225": "Stories (Missionary stories)",
"226": "Education",
"227": "Community News (Southern Union)",
"228": "Missions (Foreign Missions)",
"229": "Meeting Reports (Tract and Missionary Societies)",
"23": "Theology (Law and the New Testament)",
"230": "Spiritual Growth (Christian Life)",
"231": "Conference Proceedings (Resolutions Adopted)",
"232": "Spiritual Growth (Christian Virtue)",
"233": "Community News (Lake Union)",
"234": "Reports on the Cause (\"Progress of the Cause\" - Report of Labor)",
"235": "Theology (Christology)",
"236": "Stories (Animals)",
"237": "Periodicals (Publication Information - Michigan Titles)",
"238": "Spiritual Growth (Christian Virtue)",
"239": "Organization (Constitutions, Bylaws, and Articles of Incorporation)",
"24": "Theology (Atonement)",
"240": "Education (Lesson Plans for Sabbath Study)",
"241": "Bible (Old Testament)",
"242": "Missions (Of Missionary Ships)",
"243": "Signs of the Times (Enforcement of Sunday Laws)",
"244": "Spiritual Growth (Christian Education)",
"245": "Periodicals (Washington, D.C. Titles)",
"246": "Nutrition (Food)",
"247": "Health (Dress Reform)",
"248": "Organization (Divisions)",
"249": "Missions (Missions Department)",
"25": "Theology (Tithing)",
"250": "Health (Exercise)",
"26": "Organization (Notices of Meetings)",
"27": "Religious Commentary (Spiritualism)",
"28": "Signs of the Times (\"Eastern Question\")",
"29": "Meeting Reports (Accounts of Camp Meetings and Conferences)",
"3": "Scan Errors (OCR Errors)",
"30": "Advertisements (Publications) ",
"31": "Politics (War and the State)",
"32": "Health (Disease)",
"33": "Missions (Canvassing Workers)",
"34": "Theology (Great Controversy)",
"35": "Advertisements (SDA Publications - mid)",
"36": "Bible (Translations)",
"37": "Theology (Sin)",
"38": "Religious Commentary (Descriptions of Heaven)",
"39": "Theology (God and Man)",
"4": "Social Commentary (Suffering and Death from Vices)",
"40": "Signs of the Times (Social Unrest)",
"41": "Theology (Bible Interpretation)",
"42": "Nutrition (Vegetables and Produce)",
"43": "Church & State (Opposition to Religious Legislation)",
"44": "Periodicals (Agencies for Magazine Ordering)",
"45": "Missions (Chicago Mission)",
"46": "Prophecy (Figures of Daniel) ",
"47": "Transportation (Train Travel)",
"48": "Health (Infant Care)",
"49": "Correspondence",
"5": "Spiritual Growth (Christian Life - Perseverance)",
"50": "Periodicals (Book Sales and Publishing Business)",
"51": "Spiritual Growth (Calls to Christian Virtue - EGW)",
"52": "Eschatology (Spreading the Third Angel's Message)",
"53": "Bible (Parables - Wealth)",
"54": "Bible (Parables - Talents)",
"55": "Meeting Reports (Lake Union Conferences)",
"56": "Community News (Columbia Union)",
"57": "History (Historical Evidence for Reliability of Bible)",
"58": "History (Religious Liberty in Anglo Political History)",
"59": "Organization (The Chicago Mission)",
"6": "Sermons (Religious Practice)",
"60": "Correspondence (Letters from Readers)",
"61": "Reports on the Cause (Account of Labors)",
"62": "Meeting Reports (Descriptions of Denominational Events)",
"63": "Nature (Landscapes)",
"64": "Missions (Asia)",
"65": "Health (Cleaning - teeth and household)",
"66": "Education (Reading Course)",
"67": "Nutrition (Diet)",
"68": "Missions (Calls to Home Missions - EGW)",
"69": "Advertisements (Health)",
"7": "Bible (Stories from Daniel and Babylonian Captivity)",
"70": "Organization (Funds - Harvest Ingathering)",
"71": "Missions (Tract Distribution)",
"72": "Meeting Reports (Southern Union Conferences)",
"73": "Theology (the Dead)",
"74": "Apologetics (Debates)",
"75": "Missions (Foreign Missions)",
"76": "General Interest (Military Culture)",
"77": "General Interest (Architecture)",
"78": "Bible (Old Testament Lessons)",
"79": "Advertisements (Goods and Services)",
"8": "Scan Errors (OCR Errors 2)",
"80": "Stories (Character Development - Boys)",
"81": "Bible (Biblical Exegesis)",
"82": "Stories (Moralistic Stories - girls)",
"83": "Organization (Travel Arrangements and Organization)",
"84": "Social Commentary (Marriage and Divorce)",
"85": "Spiritual Growth (Virtuousness and Industry)",
"86": "Social Commentary (Amusement and Sport)",
"87": "Signs of the Times (Growing Iniquity as in Days of Noah)",
"88": "Advertisements (Subscription)",
"89": "Bible (New Testament)",
"9": "Spiritual Growth (Christian Behavior)",
"90": "Social Commentary (Immigration and Non-English Language Concerns)",
"91": "Missions (Relief for Indigent Children)",
"92": "Advertisements (Music and Instruments)",
"93": "Theology (Fate of the Wicked at Second Coming)",
"94": "Health (Tuberculosis)",
"95": "Spiritual Growth (Manners and Cheerfulness)",
"96": "Health (Hydrotherapy)",
"97": "General Interest (News and Catastrophic Events)",
"98": "Health (Q & A)",
"99": "Health (Coffee Tea Tobacco)"
}
In [ ]: