Commit Live PR

README.md

@@ -10,7 +10,7 @@ Doing this project will enable you to integrate Multiple data sources to answer
 You also learn to perform common excel tasks with pandas
 
 
-## What will you learn in the session ?
+## What will you learn in the session?
 - Python Basics
 - Pandas
 - Web Scrapping
@@ -20,4 +20,4 @@ You also learn to perform common excel tasks with pandas
 
 ## Pre-requisites
 - Working knowledge of Pandas, Numpy, Matplotlib
-- Data indexing and slicing
+- Data indexing along with slicing

q01_load_data.ipynb

@@ -13,4 +13,4 @@
  "metadata": {},
  "nbformat": 4,
  "nbformat_minor": 2
-}
+} 

q01_load_data/build.py

@@ -1,5 +1,11 @@
+# %load q01_load_data/build.py
 import pandas as pd
-
+path = 'data/excel-comp-data.xlsx'
 
 def q01_load_data(path):
-    "write your solution here"
+    df = pd.read_excel(path)
+    df['state'] = df['state'].str.lower()
+    df['total'] = df['Jan'] + df['Feb'] + df['Mar']
+    return df
+q01_load_data(path)
+

q02_append_row/build.py

@@ -1,12 +1,16 @@
 import pandas as pd
 import sys, os
-#sys.path.append(os.path.join(os.path.dirname(os.curdir)))
 from greyatomlib.pandas_guided_project.q01_load_data.build import q01_load_data
 
-
 def q02_append_row(path):
-    "write your solution here"
-
-
+    df = q01_load_data(path)
+    df1 = df[['Jan', 'Feb', 'Mar', 'total']].sum(axis=0)
+    df1 = pd.DataFrame(df1)
+    df2 = pd.DataFrame(columns=['Jan', 'Feb', 'Mar', 'total'])
+    df2['Jan'] = df1.loc['Jan']
+    df2['Feb'] = df1.loc['Feb']
+    df2['Mar'] = df1.loc['Mar']
+    df2['total'] = df1.loc['total']
+    df3 = df.append(df2, ignore_index=True)
 
 

q03_scrape_clean/build.py

@@ -5,5 +5,26 @@
 
 
 def q03_scrape_clean(url):
-    "write your solution here"
+    page = requests.get(url)
+
+    df = pd.read_html(page.text)
+    df1 = df[0].iloc[11:,0]
+    df2 = df[0].iloc[11:,1]
+    df3 = df[0].iloc[11:,2]
+    df4 = df[0].iloc[11:,3]
+    df5 = df[0].iloc[11:,4]
+    df6 = df[0].iloc[11:,5]
+    df7 = df[0].iloc[11:,6]
+    df8 = df[0].iloc[11:,7]
+    df9 = df[0].iloc[11:,8]
+    df10 = df[0].iloc[11:,9]
+
+    ans = pd.concat([df1,df2,df3,df4,df5,df6,df7,df8,df9,df10], axis=1)
+    ans.rename(mapper={0:'Name', 1:'Status', 2:'ISO', 3:'ANSI0', 4:'ANSI1', 5:'USPS', 6:'USCG', 7:'GPO', 8:'AP', 9:'Other Abbrevations'}, inplace=True, axis=1)
+    ans.drop(ans.index[0], axis=0, inplace=True)
+    ans['ex1'] = 0
+    ans['ex2'] = 0
+    ans['ex3'] = 0
+    ans['ex4'] = 0
+    ans['ex5'] = 0