DataGlacier · ALLEN-AYODEJI · Apr 6, 2022 · Apr 7, 2022 · Apr 14, 2022
diff --git a/.DS_Store b/.DS_Store
diff --git a/.ipynb_checkpoints/EDA Notebook-checkpoint.ipynb b/.ipynb_checkpoints/EDA Notebook-checkpoint.ipynb
diff --git a/Data Intake Report.pdf b/Data Intake Report.pdf
diff --git a/EDA Notebook.ipynb b/EDA Notebook.ipynb
diff --git a/README.md b/README.md
@@ -1 +1,3 @@
 # G2M Cab DataSets
+## Resources
+https://github.com/DataGlacier/DataSets.git
diff --git a/city_data_cleaned.csv b/city_data_cleaned.csv
@@ -0,0 +1,21 @@
+,City,Population,Users
+0,NEW YORK NY," 8,405,837 "," 302,149 "
+1,CHICAGO IL," 1,955,130 "," 164,468 "
+2,LOS ANGELES CA," 1,595,037 "," 144,132 "
+3,MIAMI FL," 1,339,155 "," 17,675 "
+4,SILICON VALLEY," 1,177,609 "," 27,247 "
+5,ORANGE COUNTY," 1,030,185 "," 12,994 "
+6,SAN DIEGO CA," 959,307 "," 69,995 "
+7,PHOENIX AZ," 943,999 "," 6,133 "
+8,DALLAS TX," 942,908 "," 22,157 "
+9,ATLANTA GA," 814,885 "," 24,701 "
+10,DENVER CO," 754,233 "," 12,421 "
+11,AUSTIN TX," 698,371 "," 14,978 "
+12,SEATTLE WA," 671,238 "," 25,063 "
+13,TUCSON AZ," 631,442 "," 5,712 "
+14,SAN FRANCISCO CA," 629,591 "," 213,609 "
+15,SACRAMENTO CA," 545,776 "," 7,044 "
+16,PITTSBURGH PA," 542,085 "," 3,643 "
+17,WASHINGTON DC," 418,859 "," 127,001 "
+18,NASHVILLE TN," 327,225 "," 9,270 "
+19,BOSTON MA," 248,968 "," 80,021 "
diff --git a/data_cleaning.csv b/data_cleaning.csv
diff --git a/data_cleaning.py b/data_cleaning.py
@@ -0,0 +1,15 @@
+import pandas as pd
+df1= pd.read_csv('Cab_Data.csv')
+df2= pd.read_csv('Transaction_ID.csv')
+df3= pd.read_csv('Customer_ID.csv')
+
+inner = pd.merge(df1, df2) 
+
+new_dataframe = pd.merge(inner, df3)
+
+new_dataframe_out = new_dataframe.drop(["0"], axis = 1)
+
+
+
+
+
diff --git a/data_cleaning_2.py b/data_cleaning_2.py
@@ -0,0 +1,5 @@
+import pandas as pd
+
+df = pd.read_csv('City.csv')
+
+df.to_csv("city_data_cleaned.csv")