commit-live-students · Tusharshah2006 · Aug 18, 2018 · Aug 18, 2018 · Aug 18, 2018 · Aug 18, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/__pycache__/build.cpython-36.pyc b/q01_load_data/__pycache__/build.cpython-36.pyc
diff --git a/q01_load_data/build.py b/q01_load_data/build.py
@@ -1,5 +1,14 @@
+# %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.iloc[:,6:9].sum(axis=1)
+
+    return df
+
+q01_load_data(path)
+
+
diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/tests/__pycache__/tests.cpython-36.pyc b/q01_load_data/tests/__pycache__/tests.cpython-36.pyc
diff --git a/q02_append_row/__pycache__/__init__.cpython-36.pyc b/q02_append_row/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_append_row/__pycache__/build.cpython-36.pyc b/q02_append_row/__pycache__/build.cpython-36.pyc
diff --git a/q02_append_row/build.py b/q02_append_row/build.py
@@ -1,12 +1,19 @@
+# %load q02_append_row/build.py
 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
 
+path = 'data/excel-comp-data.xlsx'
 
 def q02_append_row(path):
-    "write your solution here"
+    df = q01_load_data(path)
+    df.loc[len(df)] = df.iloc[:,6:10].sum(axis=0) 
 
+    df.fillna(value=0, inplace=True, axis=0)
+
+    return df
 
+q02_append_row(path)
 
 
diff --git a/q02_append_row/tests/__pycache__/__init__.cpython-36.pyc b/q02_append_row/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_append_row/tests/__pycache__/tests.cpython-36.pyc b/q02_append_row/tests/__pycache__/tests.cpython-36.pyc
diff --git a/q03_scrape_clean/__pycache__/__init__.cpython-36.pyc b/q03_scrape_clean/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_scrape_clean/__pycache__/build.cpython-36.pyc b/q03_scrape_clean/__pycache__/build.cpython-36.pyc
diff --git a/q03_scrape_clean/build.py b/q03_scrape_clean/build.py
@@ -1,9 +1,20 @@
+# %load q03_scrape_clean/build.py
 import pandas as pd
 import sys, os
 import requests
+from bs4 import BeautifulSoup
 sys.path.append(os.path.join(os.path.dirname(os.curdir)))
 
 
 def q03_scrape_clean(url):
-    "write your solution here"
+    response = requests.get(url)
+    soup = BeautifulSoup(response.content,'lxml')
+    table = soup.find_all('table')[0]
+    df = pd.read_html(str(table))[0]
+    df = df.iloc[12:,:]
+
+    return df
+
+q03_scrape_clean('https://en.wikipedia.org/wiki/List_of_U.S._state_abbreviations')
+
 
diff --git a/q03_scrape_clean/tests/__pycache__/__init__.cpython-36.pyc b/q03_scrape_clean/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_scrape_clean/tests/__pycache__/tests.cpython-36.pyc b/q03_scrape_clean/tests/__pycache__/tests.cpython-36.pyc
diff --git a/q04_mapping/__pycache__/__init__.cpython-36.pyc b/q04_mapping/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_mapping/__pycache__/build.cpython-36.pyc b/q04_mapping/__pycache__/build.cpython-36.pyc
diff --git a/q04_mapping/build.py b/q04_mapping/build.py
@@ -1,10 +1,27 @@
+# %load q04_mapping/build.py
 import pandas as pd
 import sys, os
 import numpy as np
 #sys.path.append(os.path.join(os.path.dirname(os.curdir)))
+from greyatomlib.pandas_guided_project.q01_load_data.build import q01_load_data
 from greyatomlib.pandas_guided_project.q02_append_row.build import q02_append_row
-def q04_mapping(path1,path2):
-    "write your solution here"
+path1 = 'data/excel-comp-data.xlsx'
+path2 = 'data/scraped.csv'
 
+def q04_mapping(path1, path2):
+    df_02 = q01_load_data(path1)
+    df_02.loc[len(df_02)] = df_02.iloc[:,6:10].sum(axis=0) 
+    df_02.fillna(value=0, inplace=True, axis=0)
+
+    #df_02 = q02_append_row(path1)
+    df_03 = pd.read_csv(path2)   
+    mapping = dict(zip(df_03['United States of America'].str.lower(), df_03['Unnamed: 6']))
+
+    df_02.insert(loc=6, column='abbr', value='')
+    df_02.iloc[:,6]=df_02['state'].map(mapping)
+
+    return df_02 
+
+q04_mapping(path1, path2)
 
 
diff --git a/q04_mapping/tests/__pycache__/__init__.cpython-36.pyc b/q04_mapping/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_mapping/tests/__pycache__/test.cpython-36.pyc b/q04_mapping/tests/__pycache__/test.cpython-36.pyc
diff --git a/q05_replace_missing_values/__pycache__/__init__.cpython-36.pyc b/q05_replace_missing_values/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_replace_missing_values/__pycache__/build.cpython-36.pyc b/q05_replace_missing_values/__pycache__/build.cpython-36.pyc
diff --git a/q05_replace_missing_values/build.py b/q05_replace_missing_values/build.py
@@ -1,13 +1,32 @@
+# %load q05_replace_missing_values/build.py
 import pandas as pd
 import numpy as np
 import sys
 import 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
 from greyatomlib.pandas_guided_project.q04_mapping.build import q04_mapping
 
 path1 = 'data/excel-comp-data.xlsx'
 path2 = 'data/scraped.csv'
 def q05_replace_missing_values(path1,path2):
 
+    df_02 = q01_load_data(path1)
+    df_02.loc[len(df_02)] = df_02.iloc[:,6:10].sum(axis=0) 
+    df_02.fillna(value=0, inplace=True, axis=0)
+
+    df_03 = pd.read_csv(path2)   
+    mapping = dict(zip(df_03['United States of America'].str.lower(), df_03['Unnamed: 6']))
+
+    df_02.insert(loc=6, column='abbr', value='')
+    df_02.iloc[:,6]=df_02['state'].map(mapping)
+
+    #df_02 = q04_mapping (path1, path2)
+    df_02.iloc[6,6] = 'MS'
+    df_02.iloc[10,6] = 'TN'
+
+    return df_02 
+
+print(q05_replace_missing_values(path1,path2).shape)
+
 
-#print(q05_replace_missing_values(path1,path2).shape)
diff --git a/q05_replace_missing_values/tests/__pycache__/__init__.cpython-36.pyc b/q05_replace_missing_values/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_replace_missing_values/tests/__pycache__/tests.cpython-36.pyc b/q05_replace_missing_values/tests/__pycache__/tests.cpython-36.pyc
diff --git a/q06_sub_total/__pycache__/__init__.cpython-36.pyc b/q06_sub_total/__pycache__/__init__.cpython-36.pyc
diff --git a/q06_sub_total/__pycache__/build.cpython-36.pyc b/q06_sub_total/__pycache__/build.cpython-36.pyc
diff --git a/q06_sub_total/build.py b/q06_sub_total/build.py
@@ -1,16 +1,35 @@
+# %load q06_sub_total/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 import sys
 import 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
 from greyatomlib.pandas_guided_project.q05_replace_missing_values.build import q05_replace_missing_values
 
 path1 = 'data/excel-comp-data.xlsx'
 path2 = 'data/scraped.csv'
 
 def q06_sub_total(path1,path2):
-    "write your solution here"
+    df_02 = q01_load_data(path1)
+    df_02.loc[len(df_02)] = df_02.iloc[:,6:10].sum(axis=0) 
+    df_02.fillna(value=0, inplace=True, axis=0)
+
+    df_03 = pd.read_csv(path2)   
+    mapping = dict(zip(df_03['United States of America'].str.lower(), df_03['Unnamed: 6']))
 
+    df_02.insert(loc=6, column='abbr', value='')
+    df_02.iloc[:,6]=df_02['state'].map(mapping)
+
+    df_02.iloc[6,6] = 'MS'
+    df_02.iloc[10,6] = 'TN'
+
+    #df_02 = q05_replace_missing_values(path1,path2)
+    df_sub = df_02.groupby(['abbr'])[['account', 'Jan', 'Feb', 'Mar']].sum()
+
+    return df_sub
+
+q06_sub_total(path1,path2)
 
 
diff --git a/q06_sub_total/tests/__pycache__/__init__.cpython-36.pyc b/q06_sub_total/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q06_sub_total/tests/__pycache__/test.cpython-36.pyc b/q06_sub_total/tests/__pycache__/test.cpython-36.pyc
diff --git a/q07_symbols/__pycache__/__init__.cpython-36.pyc b/q07_symbols/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_symbols/__pycache__/build.cpython-36.pyc b/q07_symbols/__pycache__/build.cpython-36.pyc
diff --git a/q07_symbols/build.py b/q07_symbols/build.py
@@ -1,18 +1,36 @@
+# %load q07_symbols/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 import sys
 import os
 sys.path.append(os.path.join(os.path.dirname(os.curdir)))
-from greyatomlib.pandas_guided_project.q06_sub_total.build import q06_sub_total
+
+from greyatomlib.pandas_guided_project.q01_load_data.build import q01_load_data
+#from greyatomlib.pandas_guided_project.q06_sub_total.build import q06_sub_total
 
 path1 = 'data/excel-comp-data.xlsx'
 path2 = 'data/scraped.csv'
 
 def q07_symbols(path1,path2):
-    "write your solution here"
+    df_02 = q01_load_data(path1)
+    df_02.loc[len(df_02)] = df_02.iloc[:,6:10].sum(axis=0) 
+    df_02.fillna(value=0, inplace=True, axis=0)
+
+    df_03 = pd.read_csv(path2)   
+    mapping = dict(zip(df_03['United States of America'].str.lower(), df_03['Unnamed: 6']))
+
+    df_02.insert(loc=6, column='abbr', value='')
+    df_02.iloc[:,6]=df_02['state'].map(mapping)
+
+    df_02.iloc[6,6] = 'MS'
+    df_02.iloc[10,6] = 'TN'
 
+    #df_sub = q06_sub_total(path1,path2)   
+    df_sub = df_02.groupby(['abbr'])[['account', 'Jan', 'Feb', 'Mar', 'total']].sum().applymap(lambda x: '$%s'% '{:,}'.format(int(x)))
+
+    return df_sub
 
+q07_symbols(path1,path2)
 
-#print(q07_symbols(path1,path2))
 
diff --git a/q07_symbols/tests/__pycache__/__init__.cpython-36.pyc b/q07_symbols/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_symbols/tests/__pycache__/test.cpython-36.pyc b/q07_symbols/tests/__pycache__/test.cpython-36.pyc
diff --git a/q08_append_subtotals/__pycache__/__init__.cpython-36.pyc b/q08_append_subtotals/__pycache__/__init__.cpython-36.pyc
diff --git a/q08_append_subtotals/__pycache__/build.cpython-36.pyc b/q08_append_subtotals/__pycache__/build.cpython-36.pyc
diff --git a/q08_append_subtotals/build.py b/q08_append_subtotals/build.py
@@ -1,15 +1,37 @@
+# %load q08_append_subtotals/build.py
 import pandas as pd
 import numpy as np
 import sys,os
 #sys.path.append(os.path.join(os.path.dirname(os.curdir)))
-from greyatomlib.pandas_guided_project.q06_sub_total.build import q06_sub_total
-from greyatomlib.pandas_guided_project.q07_symbols.build import q07_symbols
-
+from greyatomlib.pandas_guided_project.q01_load_data.build import q01_load_data
+#from greyatomlib.pandas_guided_project.q06_sub_total.build import q06_sub_total
+#from greyatomlib.pandas_guided_project.q07_symbols.build import q07_symbols
 
 path1 = 'data/excel-comp-data.xlsx'
 path2 = 'data/scraped.csv'
 
 def q08_append_subtotals(path1,path2):
-    "write your solution here"
+    df_02 = q01_load_data(path1)
+    df_02.loc[len(df_02)] = df_02.iloc[:,6:10].sum(axis=0) 
+    df_02.fillna(value=0, inplace=True, axis=0)
+
+    df_03 = pd.read_csv(path2)   
+    mapping = dict(zip(df_03['United States of America'].str.lower(), df_03['Unnamed: 6']))
+
+    df_02.insert(loc=6, column='abbr', value='')
+    df_02.iloc[:,6]=df_02['state'].map(mapping)
+
+    df_02.iloc[6,6] = 'MS'
+    df_02.iloc[10,6] = 'TN'
+
+    #df_sub = q06_sub_total(path1,path2)
+    df_sub = df_02.groupby(['abbr'])[['Jan', 'Feb', 'Mar', 'total']].sum()
+    df_sub.loc[len(df_sub)] = df_sub.iloc[:].sum(axis=0)
+
+    df_sub = df_sub.applymap(lambda x: '$%s'% '{:,}'.format(int(x)))
+
+    return df_sub
+
+q08_append_subtotals(path1,path2)
 
 
diff --git a/q08_append_subtotals/tests/__pycache__/__init__.cpython-36.pyc b/q08_append_subtotals/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q08_append_subtotals/tests/__pycache__/tests.cpython-36.pyc b/q08_append_subtotals/tests/__pycache__/tests.cpython-36.pyc
diff --git a/q09_pie_chart_jan/__pycache__/__init__.cpython-36.pyc b/q09_pie_chart_jan/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_pie_chart_jan/__pycache__/build.cpython-36.pyc b/q09_pie_chart_jan/__pycache__/build.cpython-36.pyc
diff --git a/q09_pie_chart_jan/build.py b/q09_pie_chart_jan/build.py
@@ -1,15 +1,33 @@
+# %load q09_pie_chart_jan/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 import sys,os
 sys.path.append(os.path.join(os.path.dirname(os.curdir)))
-from greyatomlib.pandas_guided_project.q06_sub_total.build import q06_sub_total
+from greyatomlib.pandas_guided_project.q01_load_data.build import q01_load_data
+#from greyatomlib.pandas_guided_project.q06_sub_total.build import q06_sub_total
 import matplotlib.pyplot as plt
 plt.switch_backend('agg')
 
+path1 = 'data/excel-comp-data.xlsx'
+path2 = 'data/scraped.csv'
+
 def q09_pie_chart_jan(path1,path2):
+    df_02 = q01_load_data(path1)
+    df_02.loc[len(df_02)] = df_02.iloc[:,6:10].sum(axis=0) 
+    df_02.fillna(value=0, inplace=True, axis=0)
+
+    df_03 = pd.read_csv(path2)   
+    mapping = dict(zip(df_03['United States of America'].str.lower(), df_03['Unnamed: 6']))
+
+    df_02.insert(loc=6, column='abbr', value='')
+    df_02.iloc[:,6]=df_02['state'].map(mapping)
 
-    "write your solution here"
+    df_02.iloc[6,6] = 'MS'
+    df_02.iloc[10,6] = 'TN'
+
+    return df_02[['Jan', 'Feb', 'Mar', 'total']].Jan.value_counts().plot(kind='pie', y='Jan')
 
+q09_pie_chart_jan(path1,path2)
 
 
diff --git a/q09_pie_chart_jan/tests/__pycache__/__init__.cpython-36.pyc b/q09_pie_chart_jan/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_pie_chart_jan/tests/__pycache__/tests.cpython-36.pyc b/q09_pie_chart_jan/tests/__pycache__/tests.cpython-36.pyc