Initial Commit

NaiveBayes.py

+import os
+import math
+from typing import List
+a = 1
+k = 1
+
+class NaiveBayes:
+    def __init__(self, data_folder, train_subfolder, validate_subfolder, c1_folder, c2_folder):
+        self.data_folder = data_folder
+        self.train_subfolder = train_subfolder
+        self.validate_subfolder = validate_subfolder
+        self.c1_folder = c1_folder
+        self.c2_folder = c2_folder
+
+    # TODO: Implement Naive Bayes training
+    def train(self, c1_files: List[str], c2_files: List[str]):
+        pass
+
+    # TODO: Implement Naive Bayes classification
+    def classify(self, files: List[str], folder: str):
+        pass
+
+    # expect outputted lines in form "file.txt classification"
+    def create_file_to_class_dict(self, folder):
+        file_name = self.data_folder + "_" + folder + ".txt"
+        path_name = os.path.join(self.data_folder, file_name)
+        f = open(path_name, "r")
+        file_to_class = {}
+        for line in f.readlines():
+            line = line[:-1]
+            file_class = line.split(" ")
+            file = file_class[0]
+            classification = file_class[1]
+            assert(file not in file_to_class)
+            file_to_class[file] = classification
+        return file_to_class
+
+    def validate_classification(self, folder):
+        f = open("classification.txt", "r")
+        correct_dict = {}
+        incorrect_dict = {}
+
+        file_to_proper_class = self.create_file_to_class_dict(folder)
+        for line in f.readlines():
+            line = line[:-1]
+            file_class = line.split(" ")
+            file = file_class[0]
+            classification = file_class[1]
+            assert(file in file_to_proper_class)
+            if file_to_proper_class[file] == classification:
+                if classification not in correct_dict:
+                    correct_dict[classification] = 0
+                    incorrect_dict[file_to_proper_class[file]] = 0
+                correct_dict[classification] += 1
+            else:
+                if file_to_proper_class[file] not in incorrect_dict:
+                    incorrect_dict[file_to_proper_class[file]] = 0
+                    correct_dict[classification] = 0
+                incorrect_dict[file_to_proper_class[file]] += 1
+
+        print("correctly classed as: ")
+        for classification in correct_dict.keys():
+            print(classification + ": " + str(correct_dict[classification]))
+        print("incorrectly classed as: ")
+        for classification in incorrect_dict.keys():
+            print(classification + ": " + str(incorrect_dict[classification]))
+
+    def token_set(self, file: str, folder_path: str):
+        file_path_name = os.path.join(folder_path, file)
+        f = open(file_path_name, "r")
+        tokens = set()
+        for line in f.readlines():
+            line = line[:-1]
+            line_tokens = line.split(' ')
+            for token in line_tokens:
+                if len(token) > 0:
+                    token = token.lower()
+                    tokens.add(token)
+        f.close()
+        return tokens

README.md

+# bayes
+

SpamFilterMain.py

+import os
+from NaiveBayes import NaiveBayes
+
+# adult income - https://www.kaggle.com/code/prashant111/naive-bayes-classifier-in-python/data
+# tennis games - https://www.kaggle.com/code/pranavpandey2511/naive-bayes-classifier-from-scratch/data
+# ionosphere - https://archive.ics.uci.edu/ml/datasets/Ionosphere 
+# enron spam - https://www.kaggle.com/datasets/wanderfj/enron-spam 
+
+DATA_FOLDER = "emails"
+TRAIN_SUBFOLDER = "train"
+VALIDATE_SUBFOLDER = "validate"
+C1_FOLDER = "spam"
+C2_FOLDER = "ham"
+
+def main():
+    cwd = os.getcwd()
+    print("Directory: " + cwd)
+    path = DATA_FOLDER
+    train_path = os.path.join(path, TRAIN_SUBFOLDER)
+    validate_path = os.path.join(path, VALIDATE_SUBFOLDER)
+
+    train_c1_path = os.path.join(train_path, C1_FOLDER)
+    train_c2_path = os.path.join(train_path, C2_FOLDER)
+    train_c1 = os.listdir(train_c1_path)
+    train_c2 = os.listdir(train_c2_path)
+
+    valid_files = os.listdir(validate_path)
+    
+    if sanity_check(train_c1, train_c2, valid_files):
+        nb = NaiveBayes(DATA_FOLDER, TRAIN_SUBFOLDER, VALIDATE_SUBFOLDER, C1_FOLDER, C2_FOLDER)
+        nb.train(train_c1, train_c2)
+        nb.classify(valid_files, VALIDATE_SUBFOLDER)
+        nb.validate_classification(VALIDATE_SUBFOLDER)
+
+def sanity_check(train_c1, train_c2, valid_files):
+    pas = True
+    if train_c1 == None or len(train_c1) == 0:
+        print("Error loading positive training files")
+        pas = False
+    if train_c2 == None or len(train_c2) == 0:
+        print("Error loading negative training files")
+        pas = False
+    if valid_files == None or len(valid_files) == 0:
+        print("Error loading positive validation files")
+        pas = False
+    if not pas:
+        print("Make sure this file is in the same directory as your tweets file")
+    return pas
+
+main()
\ No newline at end of file

emails/emails_validate.txt

+1.txt spam
+10.txt spam
+100.txt ham
+101.txt ham
+102.txt spam
+103.txt spam
+104.txt ham
+105.txt ham
+106.txt spam
+107.txt spam
+108.txt ham
+109.txt ham
+11.txt ham
+110.txt spam
+111.txt ham
+112.txt ham
+113.txt ham
+114.txt spam
+115.txt ham
+116.txt spam
+117.txt spam
+118.txt ham
+119.txt spam
+12.txt spam
+120.txt ham
+121.txt ham
+122.txt spam
+123.txt ham
+124.txt spam
+125.txt ham
+126.txt spam
+127.txt ham
+128.txt ham
+129.txt spam
+13.txt ham
+130.txt ham
+131.txt ham
+132.txt ham
+133.txt ham
+134.txt ham
+135.txt ham
+136.txt ham
+137.txt ham
+138.txt spam
+139.txt ham
+14.txt spam
+140.txt ham
+141.txt ham
+142.txt ham
+143.txt ham
+144.txt ham
+145.txt spam
+146.txt ham
+147.txt ham
+148.txt ham
+149.txt spam
+15.txt spam
+150.txt spam
+151.txt ham
+152.txt ham
+153.txt ham
+154.txt spam
+155.txt ham
+156.txt ham
+157.txt ham
+158.txt ham
+159.txt spam
+16.txt spam
+160.txt spam
+161.txt spam
+162.txt ham
+163.txt spam
+164.txt spam
+165.txt spam
+166.txt ham
+167.txt ham
+168.txt ham
+169.txt ham
+17.txt ham
+170.txt ham
+171.txt ham
+172.txt spam
+173.txt ham
+174.txt ham
+175.txt ham
+176.txt spam
+177.txt ham
+178.txt ham
+179.txt ham
+18.txt spam
+180.txt ham
+181.txt ham
+182.txt spam
+183.txt ham
+184.txt ham
+185.txt ham
+186.txt ham
+187.txt ham
+188.txt ham
+189.txt ham
+19.txt ham
+190.txt ham
+191.txt ham
+192.txt spam
+193.txt ham
+194.txt ham
+195.txt ham
+196.txt ham
+197.txt ham
+198.txt ham
+199.txt spam
+2.txt ham
+20.txt ham
+200.txt spam
+201.txt ham
+202.txt spam
+203.txt ham
+204.txt ham
+205.txt ham
+206.txt ham
+207.txt spam
+208.txt spam
+209.txt ham
+21.txt spam
+210.txt spam
+211.txt ham
+212.txt ham
+213.txt spam
+214.txt ham
+215.txt ham
+216.txt spam
+217.txt ham
+218.txt spam
+219.txt spam
+22.txt ham
+220.txt ham
+221.txt ham
+222.txt ham
+223.txt spam
+224.txt ham
+225.txt ham
+226.txt spam
+227.txt ham
+228.txt ham
+229.txt ham
+23.txt spam
+230.txt ham
+231.txt spam
+232.txt ham
+233.txt ham
+234.txt ham
+235.txt spam
+236.txt ham
+237.txt ham
+238.txt spam
+239.txt ham
+24.txt spam
+240.txt ham
+241.txt ham
+242.txt ham
+243.txt ham
+244.txt ham
+245.txt spam
+246.txt ham
+247.txt ham
+248.txt ham
+249.txt ham
+25.txt spam
+250.txt ham
+251.txt spam
+252.txt ham
+253.txt ham
+254.txt ham
+255.txt ham
+256.txt spam
+257.txt ham
+258.txt ham
+259.txt ham
+26.txt spam
+260.txt ham
+261.txt ham
+262.txt ham
+263.txt spam
+264.txt ham
+265.txt ham
+266.txt ham
+267.txt ham
+268.txt ham
+269.txt ham
+27.txt ham
+270.txt ham
+271.txt ham
+272.txt ham
+273.txt ham
+274.txt ham
+275.txt ham
+276.txt ham
+277.txt ham
+278.txt ham
+279.txt spam
+28.txt ham
+280.txt ham
+281.txt ham
+282.txt ham
+283.txt spam
+284.txt ham
+285.txt spam
+286.txt spam
+287.txt ham
+288.txt ham
+289.txt ham
+29.txt ham
+290.txt ham
+291.txt ham
+292.txt ham
+293.txt ham
+294.txt ham
+295.txt spam
+296.txt spam
+297.txt ham
+298.txt ham
+299.txt ham
+3.txt ham
+30.txt spam
+300.txt ham
+301.txt ham
+302.txt spam
+303.txt ham
+304.txt ham
+305.txt ham
+306.txt spam
+307.txt ham
+308.txt ham
+309.txt ham
+31.txt ham
+310.txt spam
+311.txt ham
+312.txt ham
+313.txt spam
+314.txt ham
+315.txt ham
+316.txt ham
+317.txt ham
+318.txt ham
+319.txt ham
+32.txt ham
+320.txt ham
+321.txt ham
+322.txt ham
+323.txt spam
+324.txt ham
+325.txt ham
+326.txt spam
+327.txt ham
+328.txt ham
+329.txt spam
+33.txt ham
+330.txt ham
+331.txt ham
+332.txt spam
+333.txt ham
+334.txt spam
+335.txt ham
+336.txt ham
+337.txt ham
+338.txt ham
+339.txt ham
+34.txt spam
+340.txt ham
+341.txt spam
+342.txt spam
+343.txt ham
+344.txt spam
+345.txt ham
+346.txt ham
+347.txt ham
+348.txt ham
+349.txt ham
+35.txt spam
+350.txt ham
+351.txt spam
+352.txt ham
+353.txt ham
+354.txt ham
+355.txt ham
+356.txt ham
+357.txt ham
+358.txt spam
+359.txt ham
+36.txt ham
+360.txt spam
+361.txt ham
+362.txt ham
+363.txt ham
+364.txt ham
+365.txt ham
+366.txt spam
+367.txt ham
+368.txt ham
+369.txt ham
+37.txt ham
+370.txt ham
+371.txt ham
+372.txt ham
+373.txt ham
+374.txt ham
+375.txt spam
+376.txt spam
+377.txt ham
+378.txt ham
+379.txt ham
+38.txt ham
+380.txt ham
+381.txt ham
+382.txt ham
+383.txt ham
+384.txt spam
+385.txt ham
+386.txt ham
+387.txt spam
+388.txt ham
+389.txt ham
+39.txt ham
+390.txt ham
+391.txt ham
+392.txt ham
+393.txt spam
+394.txt spam
+395.txt spam
+396.txt spam
+397.txt ham
+398.txt ham
+399.txt ham
+4.txt ham
+40.txt ham
+400.txt ham
+401.txt ham
+402.txt ham
+403.txt ham
+404.txt spam
+405.txt ham
+406.txt ham
+407.txt ham
+408.txt spam
+409.txt spam
+41.txt ham
+410.txt spam
+411.txt ham
+412.txt ham
+413.txt ham
+414.txt spam
+415.txt spam
+416.txt spam
+417.txt ham
+418.txt ham
+419.txt ham
+42.txt ham
+420.txt ham
+421.txt spam
+422.txt ham
+423.txt spam
+424.txt ham
+425.txt spam
+426.txt spam
+427.txt ham
+428.txt ham
+429.txt ham
+43.txt spam
+430.txt ham
+431.txt spam
+432.txt ham
+433.txt ham
+434.txt ham
+435.txt spam
+436.txt ham
+437.txt ham
+438.txt ham
+439.txt spam
+44.txt ham
+440.txt ham
+441.txt spam
+442.txt ham
+443.txt ham
+444.txt spam
+445.txt ham
+446.txt ham
+447.txt ham
+448.txt ham
+449.txt ham
+45.txt ham
+450.txt ham
+451.txt spam
+452.txt spam
+453.txt spam
+454.txt spam
+455.txt ham
+456.txt ham
+457.txt ham
+458.txt ham
+459.txt spam
+46.txt ham
+460.txt ham
+461.txt spam
+462.txt ham
+463.txt ham
+464.txt spam
+465.txt spam
+466.txt spam
+467.txt ham
+468.txt spam
+469.txt ham
+47.txt spam
+470.txt ham
+471.txt spam
+472.txt ham
+473.txt ham
+474.txt ham
+475.txt ham
+476.txt ham
+477.txt ham
+478.txt ham
+479.txt ham
+48.txt ham
+480.txt ham
+481.txt spam
+482.txt ham
+483.txt ham
+484.txt ham
+485.txt ham
+486.txt spam
+487.txt spam
+488.txt spam
+489.txt spam
+49.txt ham
+490.txt ham
+491.txt ham
+492.txt ham
+493.txt ham
+494.txt ham
+495.txt spam
+496.txt ham
+497.txt ham
+498.txt spam
+499.txt ham
+5.txt ham
+50.txt spam
+500.txt ham
+51.txt ham
+52.txt ham
+53.txt spam
+54.txt ham
+55.txt ham
+56.txt spam
+57.txt ham
+58.txt spam
+59.txt spam
+6.txt ham
+60.txt ham
+61.txt spam
+62.txt ham
+63.txt spam
+64.txt spam
+65.txt ham
+66.txt ham
+67.txt spam
+68.txt ham
+69.txt ham
+7.txt ham
+70.txt ham
+71.txt ham
+72.txt ham
+73.txt ham
+74.txt ham
+75.txt spam
+76.txt ham
+77.txt ham
+78.txt ham
+79.txt ham
+8.txt ham
+80.txt ham
+81.txt spam
+82.txt ham
+83.txt ham
+84.txt ham
+85.txt ham
+86.txt spam
+87.txt spam
+88.txt ham
+89.txt ham
+9.txt spam
+90.txt ham
+91.txt spam
+92.txt ham
+93.txt ham
+94.txt ham
+95.txt spam
+96.txt ham
+97.txt ham
+98.txt ham
+99.txt spam

emails/train/ham/1.txt

+Subject: vastar resources , inc .
+gary , production from the high island larger block a - 1 # 2 commenced on
+saturday at 2 : 00 p . m . at about 6 , 500 gross . carlos expects between 9 , 500 and
+10 , 000 gross for tomorrow . vastar owns 68 % of the gross production .
+george x 3 - 6992
+- - - - - - - - - - - - - - - - - - - - - - forwarded by george weissman / hou / ect on 12 / 13 / 99 10 : 16
+am - - - - - - - - - - - - - - - - - - - - - - - - - - -
+daren j farmer
+12 / 10 / 99 10 : 38 am
+to : carlos j rodriguez / hou / ect @ ect
+cc : george weissman / hou / ect @ ect , melissa graves / hou / ect @ ect
+subject : vastar resources , inc .
+carlos ,
+please call linda and get everything set up .
+i ' m going to estimate 4 , 500 coming up tomorrow , with a 2 , 000 increase each
+following day based on my conversations with bill fischer at bmar .
+d .
+- - - - - - - - - - - - - - - - - - - - - - forwarded by daren j farmer / hou / ect on 12 / 10 / 99 10 : 34
+am - - - - - - - - - - - - - - - - - - - - - - - - - - -
+enron north america corp .
+from : george weissman 12 / 10 / 99 10 : 00 am
+to : daren j farmer / hou / ect @ ect
+cc : gary bryan / hou / ect @ ect , melissa graves / hou / ect @ ect
+subject : vastar resources , inc .
+darren ,
+the attached appears to be a nomination from vastar resources , inc . for the
+high island larger block a - 1 # 2 ( previously , erroneously referred to as the
+# 1 well ) . vastar now expects the well to commence production sometime
+tomorrow . i told linda harris that we ' d get her a telephone number in gas
+control so she can provide notification of the turn - on tomorrow . linda ' s
+numbers , for the record , are 281 . 584 . 3359 voice and 713 . 312 . 1689 fax .
+would you please see that someone contacts linda and advises her how to
+submit future nominations via e - mail , fax or voice ? thanks .
+george x 3 - 6992
+- - - - - - - - - - - - - - - - - - - - - - forwarded by george weissman / hou / ect on 12 / 10 / 99 09 : 44
+am - - - - - - - - - - - - - - - - - - - - - - - - - - -
+" linda harris " on 12 / 10 / 99 09 : 38 : 43 am
+to : george weissman / hou / ect @ ect
+cc :
+subject : hi a - 1 # 2
+effective 12 - 11 - 99
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| mscf / d | min ftp | time |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 4 , 500 | 9 , 925 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 6 , 000 | 9 , 908 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 8 , 000 | 9 , 878 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 10 , 000 | 9 , 840 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 12 , 000 | 9 , 793 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 14 , 000 | 9 , 738 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 16 , 000 | 9 , 674 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 18 , 000 | 9 , 602 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 20 , 000 | 9 , 521 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 22 , 000 | 9 , 431 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 24 , 000 | 9 , 332 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 26 , 000 | 9 , 224 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 28 , 000 | 9 , 108 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 30 , 000 | 8 , 982 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 32 , 000 | 8 , 847 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 34 , 000 | 8 , 703 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
+| | | |
+| 36 , 000 | 8 , 549 | 24 hours |
+| | | |
+| - - - - - - - - + - - - - - - - - - - + - - - - - - - - - - - |
\ No newline at end of file

emails/train/ham/10.txt

+Subject: entex transistion
+the purpose of the email is to recap the kickoff meeting held on yesterday
+with members from commercial and volume managment concernig the entex account :
+effective january 2000 , thu nguyen ( x 37159 ) in the volume managment group ,
+will take over the responsibility of allocating the entex contracts . howard
+and thu began some training this month and will continue to transition the
+account over the next few months . entex will be thu ' s primary account
+especially during these first few months as she learns the allocations
+process and the contracts .
+howard will continue with his lead responsibilites within the group and be
+available for questions or as a backup , if necessary ( thanks howard for all
+your hard work on the account this year ! ) .
+in the initial phases of this transistion , i would like to organize an entex
+" account " team . the team ( members from front office to back office ) would
+meet at some point in the month to discuss any issues relating to the
+scheduling , allocations , settlements , contracts , deals , etc . this hopefully
+will give each of you a chance to not only identify and resolve issues before
+the finalization process , but to learn from each other relative to your
+respective areas and allow the newcomers to get up to speed on the account as
+well . i would encourage everyone to attend these meetings initially as i
+believe this is a critical part to the success of the entex account .
+i will have my assistant to coordinate the initial meeting for early 1 / 2000 .
+if anyone has any questions or concerns , please feel free to call me or stop
+by . thanks in advance for everyone ' s cooperation . . . . . . . . . . .
+julie - please add thu to the confirmations distributions list
\ No newline at end of file

emails/train/ham/100.txt

+Subject: new email
+yo bro . this is my new email address . save it .
+aggie _ chico 2 @ hotmail . com .
+love you , lacy
+get your private , free email at http : / / www . hotmail . com
\ No newline at end of file

emails/train/ham/1000.txt

+Subject: re : industrials
+robert ,
+please make sure that gary gets a copy of the industrial spreadsheet . nobody
+has seen it in a few
+months . thanks , pat
+from : gary a hanks @ ect 06 / 29 / 2000 08 : 59 am
+to : daren j farmer / hou / ect @ ect , pat clynes / corp / enron @ enron
+cc :
+subject : re : industrials
+if it is the one i am thinking of it does . i haven ' t seen one for a few
+months .
+pat , will you make sure robert sends one to me via email .
+thanks
+gary
+- - - - - - - - - - - - - - - - - - - - - - forwarded by gary a hanks / hou / ect on 06 / 29 / 2000 08 : 54
+am - - - - - - - - - - - - - - - - - - - - - - - - - - -
+daren j farmer
+06 / 28 / 2000 07 : 59 pm
+to : gary a hanks / hou / ect @ ect
+cc :
+subject : re : industrials
+gary ,
+does the workhseet mentioned below assist you with the monthly operations
+related to the industrial customers ?
+d
+- - - - - - - - - - - - - - - - - - - - - - forwarded by daren j farmer / hou / ect on 06 / 28 / 2000
+07 : 57 pm - - - - - - - - - - - - - - - - - - - - - - - - - - -
+to : pat clynes / corp / enron @ enron
+cc : daren j farmer / hou / ect @ ect , gary a hanks / hou / ect @ ect
+subject : re : industrials
+first of the month industrials are coming along fine . i will finalize my
+pathing tomorrow , thursday , and set up buybacks and swings by the
+end of day friday .
+the industrial " buyback & deficiency deals " worksheet has captured the
+necessary data to help gas control & the on - call scheduler as well as
+myself and client services .
+i will have a preliminary worksheet done by the end of day friday .
+i am on vacation during the week of july 5 th thru july 10 th .
+enron north america corp .
+from : pat clynes @ enron 06 / 28 / 2000 12 : 45 pm
+to : robert e lloyd / hou / ect @ ect
+cc : daren j farmer / hou / ect @ ect
+subject : re : industrials
+robert ,
+how do we look on the industrial deadlines ? please let me know . thanks ,
+pat
+daren j farmer @ ect
+06 / 28 / 2000 11 : 19 am
+to : pat clynes / corp / enron @ enron
+cc :
+subject : industrials
+when will the buybacks and swings be set up for july ? i am a little
+concerned with the long weekend coming up . i believe that we agreed that
+these would be set up by the 3 rd work day , which would be friday the 7 th .
+( six days of flow . ) i definitely don ' t think that we should any later . it
+would be great if this could be handled sooner , miimizing our economic impact .
+additionally , we need to get the industrial spreadsheet up and running
+again . this report is very beneficial to gas control , industrial traders and
+schedulers on call .
+let me know what you think .
+d
\ No newline at end of file

emails/train/ham/1001.txt

+Subject: hr generalist for your group
+norma villarreal is the hr generalist for all of brent price ' s group and
+hector mcloughlin is the hr generalist for all the other groups / departments
+under sally beck .
+toni graham is the recruiter for all of sally beck ' s group .
+yvonne laing is the compensation specialist for all of sally beck ' s group .
+janet de la paz is the admin . support person for the hr group .
+i hope this helps you directs your questions or needs for services in the
+future .
\ No newline at end of file

emails/train/ham/1002.txt

+Subject: nom change for increased midcon gas . . .
+- - - - - - - - - - - - - - - - - - - - - - forwarded by ami chokshi / corp / enron on 06 / 29 / 2000
+02 : 50 pm - - - - - - - - - - - - - - - - - - - - - - - - - - -
+royal _ b _ edmondson @ reliantenergy . com on 06 / 29 / 2000 12 : 13 : 38 pm
+to : ami _ chokshi @ enron . com
+cc :
+subject : nom change for increased midcon gas . . .
+( see attached file : hpl - june . xls )
+- hpl - june . xls
\ No newline at end of file

emails/train/ham/1003.txt

+Subject: re : republic royalty 5 / 00
+done .
+daren j farmer @ ect
+06 / 29 / 2000 01 : 10 pm
+to : hillary mack / corp / enron @ enron
+cc :
+subject : re : republic royalty 5 / 00
+can you set up a gtc with duke energy field services , inc . for may - july 2000 ?
+d
+hillary mack @ enron
+06 / 29 / 2000 12 : 23 pm
+to : daren j farmer / hou / ect @ ect
+cc :
+subject : re : republic royalty 5 / 00
+daren . . . i talked to cynthia in contracts and she said that ces deals cannot
+be extended and that a new contract has to be set up . how do you want to
+handle it ?
+daren j farmer @ ect
+06 / 28 / 2000 04 : 17 pm
+to : ami chokshi / corp / enron @ enron , megan parker / corp / enron @ enron , o ' neal d
+winfree / hou / ect @ ect , nelson ferries / corp / enron @ enron , hillary
+mack / corp / enron @ enron
+cc :
+subject : re : republic royalty 5 / 00
+i have rolled # 143559 through july 2000 to cover the purchase from
+republic . we sell this gas to duke energy field services ( # 143558 for jan -
+apr , ces - duke energy field services , inc ) . the counterparty on this deal
+has been suspeneded , so i created # 316727 under the counterparty of duke
+energy field services marketing , llc .
+hillary - please extend the ces - duke counterparty or attach the correct duke
+counterparty to this deal .
+if you have any questions , let me know .
+d
+from : ami chokshi @ enron 06 / 28 / 2000 10 : 45 am
+to : megan parker / corp / enron @ enron , o ' neal d winfree / hou / ect @ ect
+cc : nelson ferries / corp / enron @ enron , daren j farmer / hou / ect @ ect
+subject : republic royalty 5 / 00
+this deal was terminated by nelson ferries .
+ami
+- - - - - - - - - - - - - - - - - - - - - - forwarded by ami chokshi / corp / enron on 06 / 28 / 2000
+10 : 42 am - - - - - - - - - - - - - - - - - - - - - - - - - - -
+from : megan parker 06 / 28 / 2000 10 : 28 am
+to : ami chokshi / corp / enron @ enron , o ' neal d winfree / hou / ect @ ect
+cc :
+subject : republic royalty 5 / 00
+republic royalty is one of my ces deals . they sent me an invoice for may
+2000 production , but i do not see a deal for may . does either of you know if
+this deal was extended under a new deal number ?
+megan
\ No newline at end of file

emails/train/ham/1004.txt

+Subject: re : republic royalty 5 / 00
+daren . . . i talked to cynthia in contracts and she said that ces deals cannot
+be extended and that a new contract has to be set up . how do you want to
+handle it ?
+daren j farmer @ ect
+06 / 28 / 2000 04 : 17 pm
+to : ami chokshi / corp / enron @ enron , megan parker / corp / enron @ enron , o ' neal d
+winfree / hou / ect @ ect , nelson ferries / corp / enron @ enron , hillary
+mack / corp / enron @ enron
+cc :
+subject : re : republic royalty 5 / 00
+i have rolled # 143559 through july 2000 to cover the purchase from
+republic . we sell this gas to duke energy field services ( # 143558 for jan -
+apr , ces - duke energy field services , inc ) . the counterparty on this deal
+has been suspeneded , so i created # 316727 under the counterparty of duke
+energy field services marketing , llc .
+hillary - please extend the ces - duke counterparty or attach the correct duke
+counterparty to this deal .
+if you have any questions , let me know .
+d
+from : ami chokshi @ enron 06 / 28 / 2000 10 : 45 am
+to : megan parker / corp / enron @ enron , o ' neal d winfree / hou / ect @ ect
+cc : nelson ferries / corp / enron @ enron , daren j farmer / hou / ect @ ect
+subject : republic royalty 5 / 00
+this deal was terminated by nelson ferries .
+ami
+- - - - - - - - - - - - - - - - - - - - - - forwarded by ami chokshi / corp / enron on 06 / 28 / 2000
+10 : 42 am - - - - - - - - - - - - - - - - - - - - - - - - - - -
+from : megan parker 06 / 28 / 2000 10 : 28 am
+to : ami chokshi / corp / enron @ enron , o ' neal d winfree / hou / ect @ ect
+cc :
+subject : republic royalty 5 / 00
+republic royalty is one of my ces deals . they sent me an invoice for may
+2000 production , but i do not see a deal for may . does either of you know if
+this deal was extended under a new deal number ?
+megan
\ No newline at end of file

emails/train/ham/1005.txt

+Subject: vacation
+i will be out on vacation the week of july 3 , back at the office on july
+10 th . my main contact will be stella morris at ext . 3319 . my desk will be
+split as follows :
+stella - nng - blackmarlin ( onshore ) , black marlin ( offshore ) , amoco third
+party , centana ( on & off system , storage ) , eastrans
+aimee - carthage , tufco updates , bridge back
+mark mccoy - katy lonestar ( on & offsystem )
+tom acton - send nominations mops to pops
+please pass this to other members of your groups , thanks .
+carlos
\ No newline at end of file

emails/train/ham/1006.txt

+Subject: vacation
+i will be out of the office next week on vacation during july 5 th through
+july 10 th .
+bob cotten will handle my entire desk . bob can be reach on extension
+3 - 6101 .
\ No newline at end of file

emails/train/ham/1007.txt

+Subject: sitara availability - status update
+we are still experiencing problems in bringing up the hardware from last
+night ' s emergency outage . as of 5 : 30 am you cannot access the application .
+every attempt is being made to rectify this problem . once the application is
+available , please stay out of position manager and use cpr positions until
+you have been notified .
+thank you for your cooperation .
+scott mills
\ No newline at end of file

emails/train/ham/1008.txt

+Subject: sitara availability this evening ( 06 / 29 ) due to emergency repairs
+sitara and cpr will be unavailable after 9 : 00 pm this evening ( 06 / 29 ) so that
+additional repairs can be made in the server room on 34 . this outage will
+impact all systems
+it is anticipated that sitara will be available beginning at 6 : 30 am tomorrow
+( 06 / 30 ) morning .
+any questions or concerns , please contact the sitara hotline ( x 37049 )
+scott mills
\ No newline at end of file

emails/train/ham/1009.txt

+Subject: hpl noms for june 30 , 2000
+( see attached file : hplo 630 . xls )
+- hplo 630 . xls
\ No newline at end of file

emails/train/ham/101.txt

+Subject: eol application id and password
+darren ,
+your id and password for eol application is as follows :
+id : dfarmer
+password : dfarmer
+this will give you read only access to the stack manager , product manager ,
+and enron online .
+if you have any questions please feel free to contact me .
+thanks
+tara
+x 34523
\ No newline at end of file

emails/train/ham/1010.txt

+Subject: enron actuals for june 28 , 2000
+teco tap 120 . 000 / hpl gas daily
+ls hpl katy 30 . 000 / enron
\ No newline at end of file

emails/train/ham/1011.txt

+Subject: revised 7 / 00 assignment , termination , expiration report - assets
+group
+we received some more name changes after the previous report was sent out .
+here is the latest & greatest version .
\ No newline at end of file