Updated lesson 5 notebooks

Author: davewhipp

notebooks/L5/Kumpula-June-2016-w-metadata.txt

@@ -0,0 +1,39 @@
+# Data file contents: Daily temperatures (mean, min, max) for Kumpula, Helsinki
+#                     for June 1-30, 2016
+# Data source: https://www.ncdc.noaa.gov/cdo-web/search?datasetid=GHCND
+# Data processing: Extracted temperatures from raw data file, converted to
+#                  comma-separated format
+#
+# David Whipp - 02.10.2017
+
+YEARMODA,TEMP,MAX,MIN
+20160601,65.5,73.6,54.7
+20160602,65.8,80.8,55.0
+20160603,68.4,,55.6
+20160604,57.5,70.9,47.3
+20160605,51.4,58.3,43.2
+20160606,52.2,59.7,42.8
+20160607,56.9,65.1,45.9
+20160608,54.2,,47.5
+20160609,49.4,54.1,45.7
+20160610,49.5,55.9,43.0
+20160611,54.0,62.1,41.7
+20160612,55.4,64.2,46.0
+20160613,58.3,68.2,47.3
+20160614,59.7,67.8,47.8
+20160615,63.4,70.3,49.3
+20160616,57.8,67.5,55.6
+20160617,60.4,70.7,55.9
+20160618,57.3,,54.0
+20160619,56.3,59.2,54.1
+20160620,59.3,69.1,52.2
+20160621,62.6,71.4,50.4
+20160622,61.7,70.2,55.4
+20160623,60.9,67.1,54.9
+20160624,61.1,68.9,56.7
+20160625,65.7,75.4,57.9
+20160626,69.6,77.7,60.3
+20160627,60.7,70.0,
+20160628,65.4,73.0,55.8
+20160629,65.8,73.2,
+20160630,65.7,72.7,59.2

notebooks/L5/exploring-data-using-pandas.ipynb

@@ -70,7 +70,7 @@
     "editable": true
    },
    "source": [
-    "**Next, we'll read the input data file**, and store the contents of that file into a variable called `data` Using the `pandas.read_csv()` -function:"
+    "**Next, we'll read the input data file**, and store the contents of that file into a variable called `data` Using the `pandas.read_csv()` function:"
    ]
   },
   {
@@ -85,7 +85,9 @@
     }
    },
    "outputs": [],
-   "source": []
+   "source": [
+    "# Read the file using pandas\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -122,9 +124,7 @@
     }
    },
    "outputs": [],
-   "source": [
-    "print(data)"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -303,13 +303,6 @@
     "No surprises here, our data variable is a Pandas DataFrame ;)."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Check more details about available paramenters and methods from [the pandas.DataFrame documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.html#pandas-dataframe)."
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -340,8 +333,7 @@
    },
    "outputs": [],
    "source": [
-    "# Display variable names:\n",
-    "%who"
+    "# Display variable names:\n"
    ]
   },
   {
@@ -350,8 +342,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Display variable name, type and info\n",
-    "%whos"
+    "# Display variable name, type and info\n"
    ]
   },
   {
@@ -621,7 +612,9 @@
     }
    },
    "outputs": [],
-   "source": []
+   "source": [
+    "# Check datatype of the column\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -656,9 +649,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "type(data.TEMP)"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -768,9 +759,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%matplotlib inline"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -784,9 +773,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "data[[\"TEMP\", \"MAX\", \"MIN\"]].plot()"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -827,9 +814,7 @@
    },
    "outputs": [],
    "source": [
-    "# Create Pandas Series from a list\n",
-    "number_series = pd.Series([ 4, 5, 6, 7.0])\n",
-    "print(number_series)"
+    "# Create Pandas Series from a list\n"
    ]
   },
   {
@@ -854,19 +839,14 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "number_series = pd.Series([ 4, 5, 6, 7.0], index=['a','b','c','d'])\n",
-    "print(number_series)"
-   ]
+   "source": []
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "type(number_series)"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -903,19 +883,14 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "new_data = pd.DataFrame(data = {\"station_name\" : stations, \"lat\" : lats, \"lon\" : lons})\n",
-    "new_data"
-   ]
+   "source": []
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "type(new_data)"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -929,17 +904,20 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "df = pd.DataFrame()"
-   ]
+   "source": []
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "print(df)"
+    "Check more details about available paramenters and methods from [the pandas.DataFrame documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.html#pandas-dataframe)."
    ]
   },
   {
@@ -956,7 +934,7 @@
  "metadata": {
   "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python [default]",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -970,7 +948,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.6"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,