hw2

HW2 Numpy

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+
+import numpy as np
+
+
+# In[2]:
+
+
+a = np.array([[1, 6], 
+              [2, 8], 
+              [3, 11],
+              [3, 10],
+              [1, 7]])
+a
+
+
+# In[8]:
+
+
+mean_a=a.mean(axis = 0)
+
+mean_a
+
+
+# In[9]:
+
+
+a_centered=np.subtract(a, mean_a)
+
+a_centered
+
+
+# In[10]:
+
+
+c = a_centered[:, 0].copy()
+
+d = a_centered[:, 1].copy()
+
+a_centered_sp=np.dot(c,d)
+a_centered_sp
+
+
+# In[12]:
+
+
+N=a.shape[0]
+N
+
+
+# In[13]:
+
+
+covar=a_centered_sp/(N-1)
+
+covar
+
+
+# In[6]:
+
+
+a_tr = np.transpose(a)
+a_tr
+cov_tr = np.cov(a_tr)
+covar2 = cov_tr[0, 1].copy()
+covar2
+

HW2 Pandas

@@ -0,0 +1,109 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[29]:
+
+
+import pandas as pd
+import numpy as np
+
+
+# In[19]:
+
+
+a = {
+    "author_id": [1, 2, 3],
+    "author_name": ['Тургенев', 'Чехов', 'Островский']
+}
+
+authors  = pd.DataFrame(a)
+
+authors 
+
+
+# In[20]:
+
+
+a = {
+    "author_id": [1, 1, 1, 2, 2, 3, 3],
+    "book_title ": ['Отцы и дети', 'Рудин', 'Дворянское гнездо', 'Толстый и тонкий', 'Дама с собачкой', 'Гроза', 'Таланты и поклонники'],
+    "price": [450, 300, 350, 500, 450, 370, 290]
+}
+
+book = pd.DataFrame(a)
+
+book  
+
+
+# In[21]:
+
+
+authors_price = authors.merge(book, left_on="author_id", right_on="author_id", how="left")
+authors_price
+
+
+# In[22]:
+
+
+top5 = authors_price.nlargest(5, "price")
+top5
+
+
+# In[23]:
+
+
+df1 = authors_price.groupby('author_name').agg({'price': 'min'}).rename(columns={'price':'min_price'})
+df1
+df2 = authors_price.groupby('author_name').agg({'price': 'max'}).rename(columns={'price':'max_price'})
+df2
+df3 = authors_price.groupby('author_name').agg({'price': 'mean'}).rename(columns={'price':'mean_price'})
+df3
+
+authors_stat = pd.concat([df1, df2, df3], axis = 1)
+authors_stat
+
+
+# In[24]:
+
+
+authors_price["cover"] = ['твердая', 'мягкая', 'мягкая', 'твердая', 'твердая', 'мягкая', 'мягкая'] 
+authors_price
+
+
+# In[42]:
+
+
+book_info = pd.pivot_table(authors_price, index=['author_name'], values="price", columns=['cover'], aggfunc=np.sum,
+                           fill_value=0)
+book_info
+
+
+# In[39]:
+
+
+get_ipython().run_line_magic('pinfo', 'pd.pivot_table')
+
+
+# In[43]:
+
+
+book_info.to_pickle("book_info.pkl")
+
+
+# In[44]:
+
+
+book_info2 = pd.read_pickle("book_info.pkl")
+
+
+# In[45]:
+
+
+book_info2
+
+
+# In[ ]:
+
+
+
+