Commit Live PR

q01_load_data/build.py

@@ -1,9 +1,22 @@
+# %load q01_load_data/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 
-
+path = 'data/perrin-freres-monthly-champagne.csv'
 def q01_load_data(path):
-    "write your solution here"
+    df = pd.read_csv(path)
+    return df.reset_index(drop=True)
 
 
+
+q01_load_data(path).shape
+df = pd.read_csv(path,index_col=False,)
+df.drop(df.index,inplace=True)
+df.head()
+df.shape
+df = pd.read_csv(path,index_col=None)
+df.head()
+df.iloc[:,0]
+
+

q02_data_splitter/build.py

@@ -1,3 +1,4 @@
+# %load q02_data_splitter/build.py
 import pandas as pd
 import numpy as np
 import datetime
@@ -6,7 +7,33 @@
 #sys.path.append('./')
 from greyatomlib.time_series_101_project.q01_load_data.build import q01_load_data
 
-
+# path = 'data/perrin-freres-monthly-champagne.csv'
 def q02_data_splitter(path):
-    data = q01_load_data(path)	
-    '''Write your solution here'''
+    data = q01_load_data(path)
+    data['Month'] = pd.to_datetime(data['Month'])
+    data['Month']=[d.date() for d in data['Month']]
+    X_train = [d for d in data['Month'] if d < datetime.date(1971, 10, 1)]
+    X_train = pd.to_datetime(X_train)
+    X_train = pd.DataFrame(X_train)
+    X_valid = [d for d in data['Month'] if d >= datetime.date(1971, 10, 1)]
+    X_valid = pd.to_datetime(X_valid)
+    X_valid = pd.DataFrame(X_valid)
+    return X_train,X_valid
+
+
+
+
+
+
+
+
+
+
+
+
+type(X_train)
+
+
+
+
+

q03_stacked_point_plot/build.py

@@ -1,3 +1,4 @@
+# %load q03_stacked_point_plot/build.py
 import pandas as pd
 import numpy as np
 #import sys
@@ -8,8 +9,17 @@
 plt.switch_backend('agg')
 import seaborn as sns
 
-def q03_stacked_point_plot(path, x_column_name="month", y_column_name="Sales", hue="year",
+def q03_stacked_point_plot(path, x_column_name='month', y_column_name='Sales', hue='year',
         order_of_the_axis=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug','Sep', 'Oct', 'Nov', 'Dec']):
     train, validation = q02_data_splitter(path)
-    #"write your solution here"
-
+    train['year'] = train['Month'].dt.year
+    train['month'] = train['Month'].dt.strftime('%b')
+    sns.pointplot(data=train,x=x_column_name,y=y_column_name,hue=train['year'],order=order_of_the_axis)
+    plt.xlabel('month')
+    plt.ylabel('Sales')
+    plt.legend(loc)
+
+    plt.show()
+
+
+

q04_boxplot/build.py

@@ -1,3 +1,4 @@
+# %load q04_boxplot/build.py
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
@@ -9,9 +10,21 @@
 # sys.path.append('./')
 from greyatomlib.time_series_101_project.q02_data_splitter.build import q02_data_splitter
 
-def q04_boxplot(path, x="month", y="Sales", kind="box", order=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug',
+def q04_boxplot(path, x='month', y='Sales', kind='box', order=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug',
        'Sep', 'Oct', 'Nov', 'Dec'], size=8):
     train, validation = q02_data_splitter(path)
-    "write your solution here"
+    sns.factorplot(data=train,x=x, y=y, kind=kind, order=order, size=size)
+    plt.xlabel('month')
+    plt.ylable('Sales')
+    plt.show()
+
 
 
+
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+sns.factorplot(data= train, x='Month', y='Sales', kind='box', order=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug',
+       'Sep', 'Oct', 'Nov', 'Dec'], size=8)
+
+