commit-live-students · vivekshingate · Sep 29, 2018 · Oct 28, 2018 · Dec 5, 2018 · Dec 6, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_rename_columns/__pycache__/__init__.cpython-36.pyc b/q01_rename_columns/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_rename_columns/__pycache__/build.cpython-36.pyc b/q01_rename_columns/__pycache__/build.cpython-36.pyc
diff --git a/q01_rename_columns/build.py b/q01_rename_columns/build.py
@@ -1,5 +1,30 @@
+# %load q01_rename_columns/build.py
 # default imports
 import pandas as pd
 
+csvPath = './data/olympics.csv'
+
+def q01_rename_columns(path):
+    df = pd.read_csv(path,skiprows=1)
+    df.rename(columns={'Unnamed: 0': 'Country',
+                       '01 !':'Gold_Summer' ,
+                       '02 !':'Silver_Summer',
+                       '03 !':'Bronze_Summer',
+                       'Total':'Total_Summer', 
+                       '01 !.1': 'Gold_Winter',
+                       '02 !.1': 'Silver_Winter' ,
+                       '03 !.1' : 'Bronze_Winter',
+                       'Total.1':'Total_Winter',
+                       '01 !.2' :'Gold_Total',
+                       '02 !.2': 'Silver_Total',
+                       '03 !.2':'Bronze_Total',
+                       'Combined total' :'Total'
+                      },inplace=True)
+    return df
+
+q01_rename_columns(csvPath)
+
+
+
 
 
diff --git a/q01_rename_columns/tests/__pycache__/__init__.cpython-36.pyc b/q01_rename_columns/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_rename_columns/tests/__pycache__/test.cpython-36.pyc b/q01_rename_columns/tests/__pycache__/test.cpython-36.pyc
diff --git a/q02_country_operations/__pycache__/__init__.cpython-36.pyc b/q02_country_operations/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_country_operations/__pycache__/build.cpython-36.pyc b/q02_country_operations/__pycache__/build.cpython-36.pyc
diff --git a/q02_country_operations/build.py b/q02_country_operations/build.py
@@ -1,8 +1,26 @@
+# %load q02_country_operations/build.py
 # default imports
 from greyatomlib.olympics_project_new.q01_rename_columns.build import q01_rename_columns
+import pandas as pd
+
 #Previous Functions
-path = "./data/olympics.csv"
-OlympicsDF=q01_rename_columns(path)    
+path = './data/olympics.csv'
+OlympicsDF=q01_rename_columns(path)
+
+def q02_country_operations(dataframe=OlympicsDF):
+    dataframe['Country_Name'] = dataframe.Country.str.split('(').str[0].str.strip()
+
+    #dataframe.Country.str.split('(') - splits the column into 2 columns viz. country and its short name
+    #.str[0] - takes the first column only discarding the country short names column
+    #.str.strip() - removes the extra space at the end of our country column
+
+    return dataframe
+
+#Call to the function
+q02_country_operations(OlympicsDF).head(150)
+
+
+
 
 
 

diff --git a/q02_country_operations/tests/__pycache__/__init__.cpython-36.pyc b/q02_country_operations/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_country_operations/tests/__pycache__/test.cpython-36.pyc b/q02_country_operations/tests/__pycache__/test.cpython-36.pyc
diff --git a/q03_better_event/__pycache__/__init__.cpython-36.pyc b/q03_better_event/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_better_event/__pycache__/build.cpython-36.pyc b/q03_better_event/__pycache__/build.cpython-36.pyc
diff --git a/q03_better_event/build.py b/q03_better_event/build.py
@@ -1,12 +1,29 @@
+# %load q03_better_event/build.py
 #default imports
 from greyatomlib.olympics_project_new.q02_country_operations.build import q02_country_operations, q01_rename_columns
 import numpy as np
+import pandas as pd
 #Previous function
-path = "./data/olympics.csv"
+path = './data/olympics.csv'
 OlympicsDF=q01_rename_columns(path)    
 OlympicsDF=q02_country_operations(OlympicsDF)
 
 
+def q03_better_event(OlympicsDF):
+    OlympicsDF['BetterEvent']=''
+
+    OlympicsDF.loc[OlympicsDF['Total_Summer']>OlympicsDF['Total_Winter'],'BetterEvent']='Summer'
+    OlympicsDF.loc[OlympicsDF['Total_Summer']<OlympicsDF['Total_Winter'],'BetterEvent']='Winter'
+    OlympicsDF.loc[OlympicsDF['Total_Summer']==OlympicsDF['Total_Winter'],'BetterEvent']='Both'
+
+    return OlympicsDF
+
+#Call to the function-
+q03_better_event(OlympicsDF)
+
+
+
+
 
 
 

diff --git a/q03_better_event/tests/__pycache__/__init__.cpython-36.pyc b/q03_better_event/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_better_event/tests/__pycache__/test.cpython-36.pyc b/q03_better_event/tests/__pycache__/test.cpython-36.pyc
diff --git a/q04_find_top_10/__pycache__/__init__.cpython-36.pyc b/q04_find_top_10/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_find_top_10/__pycache__/build.cpython-36.pyc b/q04_find_top_10/__pycache__/build.cpython-36.pyc
diff --git a/q04_find_top_10/build.py b/q04_find_top_10/build.py
@@ -1,8 +1,31 @@
+# %load q04_find_top_10/build.py
 # default imports
 from greyatomlib.olympics_project_new.q03_better_event.build import q03_better_event,q02_country_operations, q01_rename_columns
-path = "./data/olympics.csv"
+path = './data/olympics.csv'
 OlympicsDF=q01_rename_columns(path)    
 OlympicsDF=q02_country_operations(OlympicsDF)
-OlympicsDF=q03_better_event(OlympicsDF)    
+OlympicsDF=q03_better_event(OlympicsDF) 
+
+def q04_find_top_10(Dataset, col1, col2, col3):
+
+    #Getting the indices of top 10 countries event wise(viz. Summer, Winter, Total) and storing it in a variable.
+    #Dataset.iloc[0:-1,:] --> Excludes the last row which gives the total count. Hence to be excluded in analysis.
+    summer_index = Dataset.iloc[0:-1,:].sort_values(by=[col1],ascending=False).head(10).index
+    winter_index = Dataset.iloc[0:-1,:].sort_values(by=[col2],ascending=False).head(10).index
+    total_index  = Dataset.iloc[0:-1,:].sort_values(by=[col3],ascending=False).head(10).index
+
+    #Stores common index in all the above 3 lists
+    intersect_index = summer_index.intersection(winter_index).intersection(total_index)
+
+    #Separate list to store countries for each event.
+    summer_top_10_Countries = Dataset.loc[summer_index,'Country_Name']
+    winter_top_10_Countries = Dataset.loc[winter_index,'Country_Name']
+    total_top_10_Countries  = Dataset.loc[total_index,'Country_Name']
+    common_Countries        = Dataset.loc[intersect_index,'Country_Name']
+
+    return summer_top_10_Countries,winter_top_10_Countries,total_top_10_Countries,common_Countries
+
+#Call to the function -
+q04_find_top_10(OlympicsDF,'Total_Summer','Total_Winter','Total')
 
 
diff --git a/q04_find_top_10/tests/__pycache__/__init__.cpython-36.pyc b/q04_find_top_10/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_find_top_10/tests/__pycache__/test.cpython-36.pyc b/q04_find_top_10/tests/__pycache__/test.cpython-36.pyc
diff --git a/q05_top_10_plotting/__pycache__/__init__.cpython-36.pyc b/q05_top_10_plotting/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_top_10_plotting/__pycache__/build.cpython-36.pyc b/q05_top_10_plotting/__pycache__/build.cpython-36.pyc
diff --git a/q05_top_10_plotting/build.py b/q05_top_10_plotting/build.py
@@ -1,15 +1,34 @@
+# %load q05_top_10_plotting/build.py
 # default imports
 import matplotlib.pyplot as plt
+import pandas as pd
 from greyatomlib.olympics_project_new.q04_find_top_10.build import q04_find_top_10, q03_better_event, q02_country_operations, q01_rename_columns
 plt.switch_backend('agg')
-path = "./data/olympics.csv"
+path = './data/olympics.csv'
 OlympicsDF=q01_rename_columns(path)    
 OlympicsDF=q02_country_operations(OlympicsDF)
 OlympicsDF=q03_better_event(OlympicsDF)    
-Top10Summer,Top10Winter, Top10, Common =q04_find_top_10(OlympicsDF,'Total_Summer', 'Total_Winter','Total')
+Top10Summer,Top10Winter, Top10, Common = q04_find_top_10(OlympicsDF,'Total_Summer', 'Total_Winter','Total')
 
 
+def q05_top_10_plotting(Dataset,col1=Top10Summer,col2=Top10Winter,col3=Top10):
 
+    Dataset[Dataset['Country_Name'].isin(col1)].plot(x='Country_Name',y='Total_Summer',kind='bar')
+    plt.title('Top 10 Summer')
+    plt.xlabel('Country Name')
+    plt.ylabel('Total Medals')
 
+    Dataset[Dataset['Country_Name'].isin(col2)].plot(x='Country_Name',y='Total_Winter',kind='bar')
+    plt.title('Top 10 Winter')
+    plt.xlabel('Country Name')
+    plt.ylabel('Total Medals')
 
+    Dataset[Dataset['Country_Name'].isin(col3)].plot(x='Country_Name',y='Total',kind='bar')
+    plt.title('Top 10')
+    plt.xlabel('Country Name')
+    plt.ylabel('Total Medals')
+    plt.show() 
+
+#Call to the function
+q05_top_10_plotting(OlympicsDF,Top10Summer,Top10Winter,Top10)
 
diff --git a/q05_top_10_plotting/tests/__pycache__/__init__.cpython-36.pyc b/q05_top_10_plotting/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_top_10_plotting/tests/__pycache__/test.cpython-36.pyc b/q05_top_10_plotting/tests/__pycache__/test.cpython-36.pyc
diff --git a/q06_golden_winner/__pycache__/__init__.cpython-36.pyc b/q06_golden_winner/__pycache__/__init__.cpython-36.pyc
diff --git a/q06_golden_winner/__pycache__/build.cpython-36.pyc b/q06_golden_winner/__pycache__/build.cpython-36.pyc
diff --git a/q06_golden_winner/build.py b/q06_golden_winner/build.py
@@ -1,10 +1,29 @@
+# %load q06_golden_winner/build.py
 # default imports
 from greyatomlib.olympics_project_new.q04_find_top_10.build import q04_find_top_10, q03_better_event, q02_country_operations, q01_rename_columns
-path = "./data/olympics.csv"
+path = './data/olympics.csv'
 OlympicsDF=q01_rename_columns(path)    
 OlympicsDF=q02_country_operations(OlympicsDF)
 OlympicsDF=q03_better_event(OlympicsDF)    
 Top10Summer,Top10Winter, Top10, Common =q04_find_top_10(OlympicsDF,'Total_Summer', 'Total_Winter','Total')
 
+#Purposely not passing paramters inside and hadcoding instead to avoid confusion while revising.
+def q06_golden_winner(Dataset=OlympicsDF,list1=Top10Summer,list2=Top10Winter,list3=Top10):
+
+    Summer = OlympicsDF[OlympicsDF['Country_Name'].isin(Top10Summer)].loc[:,['Country_Name','Gold_Summer','Total_Summer']]
+    Summer['Gold_Ratio']=Summer['Gold_Summer']/Summer['Total_Summer']
+    Best_Country_Summer = Summer.sort_values(by='Gold_Ratio',ascending=False).iloc[0,0]
 
+    Winter = OlympicsDF[OlympicsDF['Country_Name'].isin(Top10Winter)].loc[:,['Country_Name','Gold_Winter','Total_Winter']]
+    Winter['Gold_Ratio']=Winter['Gold_Winter']/Winter['Total_Winter']
+    Best_Country_Winter = Winter.sort_values(by='Gold_Ratio',ascending=False).iloc[0,0]
+
+    Total = OlympicsDF[OlympicsDF['Country_Name'].isin(Top10)].loc[:,['Country_Name','Gold_Total','Total']]
+    Total['Gold_Ratio']=Total['Gold_Total']/Total['Total']
+    Best_Country_Total = Total.sort_values(by='Gold_Ratio',ascending=False).iloc[0,0]
+
+    return Best_Country_Summer,Best_Country_Winter,Best_Country_Total
+
+#Call to the function-
+q06_golden_winner()
 
diff --git a/q06_golden_winner/tests/__pycache__/__init__.cpython-36.pyc b/q06_golden_winner/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q06_golden_winner/tests/__pycache__/test.cpython-36.pyc b/q06_golden_winner/tests/__pycache__/test.cpython-36.pyc
diff --git a/q07_unusual_performances/__pycache__/__init__.cpython-36.pyc b/q07_unusual_performances/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_unusual_performances/__pycache__/build.cpython-36.pyc b/q07_unusual_performances/__pycache__/build.cpython-36.pyc
diff --git a/q07_unusual_performances/build.py b/q07_unusual_performances/build.py
@@ -1,5 +1,41 @@
+# %load q07_unusual_performances/build.py
 # default imports
+
+#My Solution
+import pandas as pd
 from greyatomlib.olympics_project_new.q02_country_operations.build import q02_country_operations, q01_rename_columns
-path = "./data/olympics.csv"
+path = './data/olympics.csv'
 OlympicsDF=q01_rename_columns(path)    
 OlympicsDF=q02_country_operations(OlympicsDF)
+
+def q07_unusual_performances(Dataset, lower_percentile, higher_percentile):
+
+    Lower_Quantile  = OlympicsDF['Total'].quantile(lower_percentile)
+    Higher_Quantile = OlympicsDF['Total'].quantile(higher_percentile)
+
+    OlympicsDF.drop(OlympicsDF.tail(1).index,inplace=True)
+
+    Better_Countries = OlympicsDF[OlympicsDF['Total']>Higher_Quantile]['Country_Name']
+    Worse_Countries  = OlympicsDF[OlympicsDF['Total']<=Lower_Quantile]['Country_Name']
+
+    return Worse_Countries,Better_Countries
+
+
+
+
+#Call to the function-
+q07_unusual_performances(OlympicsDF,0.05,0.95)
+#Solution that passed the test case
+def q07_unusual_performances(OlympicsDF,low,high):
+
+    OlympicsDF.drop(OlympicsDF.tail(1).index,inplace=True)
+
+    quant1=OlympicsDF['Total'].quantile(0.05)
+    quant2=OlympicsDF['Total'].quantile(0.95)
+    better=OlympicsDF[OlympicsDF['Total']>quant2]['Country_Name']
+    better=better.drop(labels=23)
+    worse=OlympicsDF[OlympicsDF['Total']<=quant1]['Country_Name']
+
+    return worse,better
+q07_unusual_performances(OlympicsDF,0.05,0.95)
+
diff --git a/q07_unusual_performances/tests/__pycache__/__init__.cpython-36.pyc b/q07_unusual_performances/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_unusual_performances/tests/__pycache__/test.cpython-36.pyc b/q07_unusual_performances/tests/__pycache__/test.cpython-36.pyc