Commit Live PR

q01_load_data/build.py

@@ -1,10 +1,22 @@
+# %load q01_load_data/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 
 
 def q01_load_data(path):
-    "write your solution here"
+    'write your solution here'
     # use .read_csv function to read the
     # data and header=0 to skip the first row
+    df = pd.read_csv(path, header=0)
+    new_header = df.iloc[0]  # grab the first row for the header
+    new_header[0] = 'country name'
+    df = df[1:]  # take the data less the header row
+    df.columns = new_header  # set the header row as the df header
+    return df
+
+
+path = 'data/olympics.csv'
+q01_load_data(path)
+
 

q02_rename_columns/build.py

@@ -1,9 +1,16 @@
+# %load q02_rename_columns/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 from greyatomlib.olympics_project.q01_load_data.build import q01_load_data
 
 def q02_rename_columns(path):
-    "write your solution here"
+    'write your solution here'
     df = q01_load_data(path)
-
+    df.rename(columns={'01 !':'Gold','02 !':'Silver','03 !':'Bronze'},inplace=True)
+    return df
+
+path='./data/olympics.csv'
+q02_rename_columns(path)
+
+

q03_split_country/build.py

@@ -2,9 +2,19 @@
 import numpy as np
 from sklearn.model_selection import train_test_split
 from greyatomlib.olympics_project.q02_rename_columns.build import q02_rename_columns
-
+import re
 
 def q03_summer_gold_medals(path):
-    "write your solution here"
+    'write your solution here'
     df = q02_rename_columns(path)
-
+    #tmp= df['country name'].apply(lambda x: re.findall('\((.*?)\)',x))
+    df['country name']=df['country name'].str.replace(r'\(([A-Za-z0-9 _]+)\)', '')
+    df['country name']=df['country name'].str.replace(r'\[([A-Za-z0-9_]+)\]', '')
+    df.index=df['country name']
+    df.drop(['country name','Totals'], axis=1,inplace=True)
+
+    return df[:-1]
+
+path='./data/olympics.csv'
+q03_summer_gold_medals(path)
+

q04_country_with_most_gold_medals/build.py

@@ -1,11 +1,17 @@
+# %load q04_country_with_most_gold_medals/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 from greyatomlib.olympics_project.q03_split_country.build import q03_summer_gold_medals
 
 
 def q04_country_with_most_gold_medals(path):
-    "write your solution here"
+    'write your solution here'
     df = q03_summer_gold_medals(path)
-
+    max_gold = df['Gold']
+    gold=pd.Series(max_gold.iloc[:,2].astype(np.int16))
+    return gold.idxmax().strip()
+
+
+q04_country_with_most_gold_medals('./data/olympics.csv')
 

q05_difference_in_gold_medal/build.py

@@ -1,9 +1,19 @@
+# %load q05_difference_in_gold_medal/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 from greyatomlib.olympics_project.q02_rename_columns.build import q02_rename_columns
+import math
+
+def q05_difference_in_gold_medal(path):
+    'write your solution here'
+    df= q02_rename_columns(path)
+    df=df[:-1]
+    df['bigg']= df['Gold'].iloc[:,0].astype(np.int16)-df['Gold'].iloc[:,1].astype(np.int16)
+    tmp=df['bigg']
+    #return df.loc[tmp.idxmax(),'country name'].strip()
+    return tmp.max()
+
+q05_difference_in_gold_medal('./data/olympics.csv')
 
-def q05_difference_in_gold_medal():
-    "write your solution here"
-
 

q06_get_points/build.py

@@ -1,9 +1,23 @@
+# %load q06_get_points/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 from greyatomlib.olympics_project.q02_rename_columns.build import q02_rename_columns
 
-path = "data/olympics.csv"
+path = 'data/olympics.csv'
+
+
+def q06_get_points(path):
+    df= q02_rename_columns(path)
+    g=df['Gold'].iloc[:,2].astype(np.int16)*3
+    b=df['Bronze'].iloc[:,2].astype(np.int16)*1
+    s=df['Silver'].iloc[:,2].astype(np.int16)*2
+    df['Points']=g+b+s
+    return df['Points']
+
+
+
+q06_get_points(path)