qiu123 · deepakush · Mar 12, 2017 · Mar 12, 2017 · Mar 12, 2017 · Mar 12, 2017
diff --git a/Applied-Machine-Learning-In-Python/certificate.pdf b/Applied-Machine-Learning-In-Python/certificate.pdf
diff --git a/Applied-Machine-Learning-In-Python/week1/Assignment1.ipynb b/Applied-Machine-Learning-In-Python/week1/Assignment1.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week1/Module1.ipynb b/Applied-Machine-Learning-In-Python/week1/Module1.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week2/Assignment2.ipynb b/Applied-Machine-Learning-In-Python/week2/Assignment2.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week2/ClassifierVisualization.ipynb b/Applied-Machine-Learning-In-Python/week2/ClassifierVisualization.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week2/Module2.ipynb b/Applied-Machine-Learning-In-Python/week2/Module2.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week3/Assignment3.ipynb b/Applied-Machine-Learning-In-Python/week3/Assignment3.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week3/Module3.ipynb b/Applied-Machine-Learning-In-Python/week3/Module3.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week4/Assignment4.ipynb b/Applied-Machine-Learning-In-Python/week4/Assignment4.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week4/Module4.ipynb b/Applied-Machine-Learning-In-Python/week4/Module4.ipynb
diff --git a/Applied-Machine-Learning-In-Python/week4/UnsupervisedLearning.ipynb b/Applied-Machine-Learning-In-Python/week4/UnsupervisedLearning.ipynb
diff --git a/Applied-Plotting-Charting-And-Data-Representation-in-Python/certificate.pdf b/Applied-Plotting-Charting-And-Data-Representation-in-Python/certificate.pdf
diff --git a/Applied-Plotting-Charting-And-Data-Representation-in-Python/week1/Cairo2015.pdf b/Applied-Plotting-Charting-And-Data-Representation-in-Python/week1/Cairo2015.pdf
diff --git a/Applied-Plotting-Charting-And-Data-Representation-in-Python/week1/Week1_Slides_Final.pdf b/Applied-Plotting-Charting-And-Data-Representation-in-Python/week1/Week1_Slides_Final.pdf
diff --git a/Applied-Plotting-Charting-And-Data-Representation-in-Python/week2/Assignment2.ipynb b/Applied-Plotting-Charting-And-Data-Representation-in-Python/week2/Assignment2.ipynb
diff --git a/Applied-Plotting-Charting-And-Data-Representation-in-Python/week2/Assignment2.py b/Applied-Plotting-Charting-And-Data-Representation-in-Python/week2/Assignment2.py
@@ -0,0 +1,121 @@
+
+# coding: utf-8
+
+# # Assignment 2
+# 
+# Before working on this assignment please read these instructions fully. In the submission area, you will notice that you can click the link to **Preview the Grading** for each step of the assignment. This is the criteria that will be used for peer grading. Please familiarize yourself with the criteria before beginning the assignment.
+# 
+# An NOAA dataset has been stored in the file `data/C2A2_data/BinnedCsvs_d100/4e86d2106d0566c6ad9843d882e72791333b08be3d647dcae4f4b110.csv`. The data for this assignment comes from a subset of The National Centers for Environmental Information (NCEI) [Daily Global Historical Climatology Network](https://www1.ncdc.noaa.gov/pub/data/ghcn/daily/readme.txt) (GHCN-Daily). The GHCN-Daily is comprised of daily climate records from thousands of land surface stations across the globe.
+# 
+# Each row in the assignment datafile corresponds to a single observation.
+# 
+# The following variables are provided to you:
+# 
+# * **id** : station identification code
+# * **date** : date in YYYY-MM-DD format (e.g. 2012-01-24 = January 24, 2012)
+# * **element** : indicator of element type
+#     * TMAX : Maximum temperature (tenths of degrees C)
+#     * TMIN : Minimum temperature (tenths of degrees C)
+# * **value** : data value for element (tenths of degrees C)
+# 
+# For this assignment, you must:
+# 
+# 1. Read the documentation and familiarize yourself with the dataset, then write some python code which returns a line graph of the record high and record low temperatures by day of the year over the period 2005-2014. The area between the record high and record low temperatures for each day should be shaded.
+# 2. Overlay a scatter of the 2015 data for any points (highs and lows) for which the ten year record (2005-2014) record high or record low was broken in 2015.
+# 3. Watch out for leap days (i.e. February 29th), it is reasonable to remove these points from the dataset for the purpose of this visualization.
+# 4. Make the visual nice! Leverage principles from the first module in this course when developing your solution. Consider issues such as legends, labels, and chart junk.
+# 
+# The data you have been given is near **None, None, Singapore**, and the stations the data comes from are shown on the map below.
+
+# In[1]:
+
+import matplotlib.pyplot as plt
+import mplleaflet
+import pandas as pd
+
+def leaflet_plot_stations(binsize, hashid):
+
+    df = pd.read_csv('data/C2A2_data/BinSize_d{}.csv'.format(binsize))
+
+    station_locations_by_hash = df[df['hash'] == hashid]
+
+    lons = station_locations_by_hash['LONGITUDE'].tolist()
+    lats = station_locations_by_hash['LATITUDE'].tolist()
+
+    plt.figure(figsize=(8,8))
+
+    plt.scatter(lons, lats, c='r', alpha=0.7, s=200)
+
+    return mplleaflet.display()
+
+leaflet_plot_stations(100,'4e86d2106d0566c6ad9843d882e72791333b08be3d647dcae4f4b110')
+
+
+# In[2]:
+
+df = pd.read_csv('data/C2A2_data/BinnedCsvs_d100/4e86d2106d0566c6ad9843d882e72791333b08be3d647dcae4f4b110.csv')
+
+
+# In[3]:
+
+df.sort(['ID','Date']).head()
+
+
+# In[4]:
+
+df['Year'], df['Month-Date'] = zip(*df['Date'].apply(lambda x: (x[:4], x[5:])))
+df = df[df['Month-Date'] != '02-29']
+
+
+# In[5]:
+
+import numpy as np
+temp_min = df[(df['Element'] == 'TMIN') & (df['Year'] != '2015')].groupby('Month-Date').aggregate({'Data_Value':np.min})
+temp_max = df[(df['Element'] == 'TMAX') & (df['Year'] != '2015')].groupby('Month-Date').aggregate({'Data_Value':np.max})
+
+
+# In[6]:
+
+temp_min.head()
+
+
+# In[7]:
+
+temp_min_15 = df[(df['Element'] == 'TMIN') & (df['Year'] == '2015')].groupby('Month-Date').aggregate({'Data_Value':np.min})
+temp_max_15 = df[(df['Element'] == 'TMAX') & (df['Year'] == '2015')].groupby('Month-Date').aggregate({'Data_Value':np.max})
+
+
+# In[8]:
+
+broken_min = np.where(temp_min_15['Data_Value'] < temp_min['Data_Value'])[0]
+broken_max = np.where(temp_max_15['Data_Value'] > temp_max['Data_Value'])[0]
+
+
+# In[9]:
+
+broken_max, broken_min
+
+
+# In[10]:
+
+temp_min_15.head()
+
+
+# In[11]:
+
+plt.figure()
+plt.plot(temp_min.values, 'b', label = 'record low')
+plt.plot(temp_max.values, 'r', label = 'record high')
+plt.scatter(broken_min, temp_min_15.iloc[broken_min], s = 10, c = 'g', label = 'broken low')
+plt.scatter(broken_max, temp_max_15.iloc[broken_max], s = 10, c = 'm', label = 'broken high')
+plt.gca().axis([-5, 370, -150, 650])
+plt.xticks(range(0, len(temp_min), 20), temp_min.index[range(0, len(temp_min), 20)], rotation = '45')
+plt.xlabel('Day of the Year')
+plt.ylabel('Temperature (Tenths of Degrees C)')
+plt.title('Temperature Summary Plot near Singapore')
+plt.legend(loc = 4, frameon = False)
+plt.gca().fill_between(range(len(temp_min)), temp_min['Data_Value'], temp_max['Data_Value'], facecolor = 'yellow', alpha = 0.5)
+plt.gca().spines['top'].set_visible(False)
+plt.gca().spines['right'].set_visible(False)
+plt.show()
+