Dataset github path updated

nursnaaz · nursnaaz · commit f23bfc0eb738 · 2019-06-22T01:25:57.000+05:30
diff --git a/Chapter01/Activities/Activity - 01 - Pre-Processing-using-Protugese-Bank-Market-Subscription-Dataset.ipynb b/Chapter01/Activities/Activity - 01 - Pre-Processing-using-Protugese-Bank-Market-Subscription-Dataset.ipynb
@@ -9,18 +9,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd    \n",
     "import numpy as np\n",
     "#reading the data into the dataframe into the object data\n",
-    "df = pd.read_csv(\"../Data/Marketing_subscription_prediction_latest_edited data.csv\", header=0)\n"
+    "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Marketing_subscription_prediction_latest_edited%20data.csv\", header=0)"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
diff --git a/Chapter01/Excercises/Excercise_01_creating_features_matrix_target_matrix.ipynb b/Chapter01/Excercises/Excercise_01_creating_features_matrix_target_matrix.ipynb
@@ -15,7 +15,7 @@
    "source": [
     "import pandas as pd \n",
     "#reading the data into the dataframe into the object data\n",
-    "df = pd.read_csv(\"../Data/USA_Housing.csv\", header=0)"
+    "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/USA_Housing.csv\", header=0)"
    ]
   },
   {
@@ -2277,7 +2277,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
diff --git a/Chapter01/Excercises/Excercise_02_remove_missing_data.ipynb b/Chapter01/Excercises/Excercise_02_remove_missing_data.ipynb
@@ -16,7 +16,7 @@
     "import pandas as pd\n",
     "\n",
     "#reading the data into the dataframe into the object data\n",
-    "df = pd.read_csv('../Data/Banking_Marketing.csv', header=0)"
+    "df = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Banking_Marketing.csv', header=0)"
    ]
   },
   {
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -58,7 +58,7 @@
        "dtype: object"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
diff --git a/Chapter01/Excercises/Excercise_03_Impute_missing_data.ipynb b/Chapter01/Excercises/Excercise_03_Impute_missing_data.ipynb
@@ -16,7 +16,7 @@
     "import pandas as pd\n",
     "\n",
     "#reading the data into the dataframe into the object data\n",
-    "df = pd.read_csv('../Data/Banking_Marketing.csv', header=0)"
+    "df = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Banking_Marketing.csv', header=0)"
    ]
   },
   {
diff --git a/Chapter01/Excercises/Excercise_04_Find_Outlier_Using_IQR.ipynb b/Chapter01/Excercises/Excercise_04_Find_Outlier_Using_IQR.ipynb
@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -18,7 +18,7 @@
     "import matplotlib.pyplot as plt\n",
     "from scipy import stats\n",
     "import numpy as np\n",
-    "df = pd.read_csv(\"../Data/german_credit_data.csv\")"
+    "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/german_credit_data.csv\")"
    ]
   },
   {
diff --git a/Chapter01/Excercises/Excercise_05_Data _Integration_merge.ipynb b/Chapter01/Excercises/Excercise_05_Data _Integration_merge.ipynb
@@ -14,8 +14,8 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "df1 = pd.read_csv('../Data/mark.csv',header = 0)\n",
-    "df2 = pd.read_csv('../Data/student.csv',header = 0)"
+    "df1 = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/mark.csv',header = 0)\n",
+    "df2 = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/student.csv',header = 0)"
    ]
   },
   {
diff --git a/Chapter01/Excercises/Excercise_06_Replacement_Method_From_Categorical_to_Numeric.py.ipynb b/Chapter01/Excercises/Excercise_06_Replacement_Method_From_Categorical_to_Numeric.py.ipynb
@@ -9,13 +9,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
     "import numpy as np\n",
-    "df = pd.read_csv(\"../Data/student.csv\")"
+    "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/student.csv\")"
    ]
   },
   {
diff --git a/Chapter01/Excercises/Excercise_07_Categorical_To_Numeric_Using_Label_Encoder.ipynb b/Chapter01/Excercises/Excercise_07_Categorical_To_Numeric_Using_Label_Encoder.ipynb
@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -18,7 +18,7 @@
     "from sklearn.preprocessing import OneHotEncoder\n",
     "\n",
     "#reading the data into the dataframe into the object data\n",
-    "df = pd.read_csv('../Data/Banking_Marketing.csv', header=0)"
+    "df = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Banking_Marketing.csv', header=0)"
    ]
   },
   {
diff --git a/Chapter01/Excercises/Excercise_08_Categorical_To_Numeric_Using_OneHot_Encoder_and_pd.get_dummies.py.ipynb b/Chapter01/Excercises/Excercise_08_Categorical_To_Numeric_Using_OneHot_Encoder_and_pd.get_dummies.py.ipynb
@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -19,7 +19,7 @@
     "from sklearn.preprocessing import OneHotEncoder\n",
     "\n",
     "#reading the data into the dataframe into the object data\n",
-    "df = pd.read_csv('../Data/Banking_Marketing.csv', header=0)\n",
+    "df = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Banking_Marketing.csv', header=0)\n",
     "df1 = df"
    ]
   },
diff --git a/Chapter01/Excercises/Excercise_09_standard_scaler.py.ipynb b/Chapter01/Excercises/Excercise_09_standard_scaler.py.ipynb
@@ -9,13 +9,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
     "from sklearn.preprocessing import StandardScaler\n",
-    "df = pd.read_csv(\"../Data/Wholesale customers data.csv\")"
+    "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Wholesale%20customers%20data.csv\")"
    ]
   },
   {
diff --git a/Chapter01/Excercises/Excercise_10_min_max_scaler.py.ipynb b/Chapter01/Excercises/Excercise_10_min_max_scaler.py.ipynb
@@ -11,22 +11,11 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/anaconda3/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: numpy.ufunc size changed, may indicate binary incompatibility. Expected 216, got 192\n",
-      "  return f(*args, **kwds)\n",
-      "/anaconda3/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: numpy.ufunc size changed, may indicate binary incompatibility. Expected 216, got 192\n",
-      "  return f(*args, **kwds)\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import pandas as pd\n",
     "from sklearn.preprocessing import MinMaxScaler\n",
-    "df = pd.read_csv(\"../Data/Wholesale customers data.csv\")"
+    "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Wholesale%20customers%20data.csv\")"
    ]
   },
   {
diff --git a/Chapter01/Excercises/Excercise_11_data_discretization.ipynb b/Chapter01/Excercises/Excercise_11_data_discretization.ipynb
@@ -9,12 +9,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "df = pd.read_csv('../Data/Student_bucketing.csv',header = 0)"
+    "df = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Student_bucketing.csv',header = 0)"
    ]
   },
   {
@@ -26,7 +26,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -111,7 +111,7 @@
        "4           5   19  1st Class       no     57"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
diff --git a/Chapter01/Excercises/Excercise_12_Train_Test_Split.py.ipynb b/Chapter01/Excercises/Excercise_12_Train_Test_Split.py.ipynb
@@ -15,7 +15,7 @@
    "source": [
     "import pandas as pd \n",
     "#reading the data into the dataframe into the object data\n",
-    "df = pd.read_csv(\"../Data/USA_Housing.csv\", header=0)"
+    "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/USA_Housing.csv\", header=0)"
    ]
   },
   {
@@ -170,7 +170,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [

Original file line number	Diff line number	Diff line change
`@@ -15,7 +15,7 @@`
`15`	`15`	`"source": [`
`16`	`16`	`"import pandas as pd \n",`
`17`	`17`	`"#reading the data into the dataframe into the object data\n",`
`18`		`- "df = pd.read_csv(\"../Data/USA_Housing.csv\", header=0)"`
	`18`	`+ "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/USA_Housing.csv\", header=0)"`
`19`	`19`	`]`
`20`	`20`	`},`
`21`	`21`	`{`
`@@ -2277,7 +2277,6 @@`
`2277`	`2277`	`]`
`2278`	`2278`	`},`
`2279`	`2279`	`{`
`2280`		`- "attachments": {},`
`2281`	`2280`	`"cell_type": "markdown",`
`2282`	`2281`	`"metadata": {},`
`2283`	`2282`	`"source": [`
Original file line number	Diff line number	Diff line change
`@@ -16,7 +16,7 @@`
`16`	`16`	`"import pandas as pd\n",`
`17`	`17`	`"\n",`
`18`	`18`	`"#reading the data into the dataframe into the object data\n",`
`19`		`- "df = pd.read_csv('../Data/Banking_Marketing.csv', header=0)"`
	`19`	`+ "df = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/Banking_Marketing.csv', header=0)"`
`20`	`20`	`]`
`21`	`21`	`},`
`22`	`22`	`{`
`@@ -28,7 +28,7 @@`
`28`	`28`	`},`
`29`	`29`	`{`
`30`	`30`	`"cell_type": "code",`
`31`		`- "execution_count": 3,`
	`31`	`+ "execution_count": 2,`
`32`	`32`	`"metadata": {},`
`33`	`33`	`"outputs": [`
`34`	`34`	`{`
`@@ -58,7 +58,7 @@`
`58`	`58`	`"dtype: object"`
`59`	`59`	`]`
`60`	`60`	`},`
`61`		`- "execution_count": 3,`
	`61`	`+ "execution_count": 2,`
`62`	`62`	`"metadata": {},`
`63`	`63`	`"output_type": "execute_result"`
`64`	`64`	`}`
Original file line number	Diff line number	Diff line change
`@@ -9,7 +9,7 @@`
`9`	`9`	`},`
`10`	`10`	`{`
`11`	`11`	`"cell_type": "code",`
`12`		`- "execution_count": 22,`
	`12`	`+ "execution_count": 1,`
`13`	`13`	`"metadata": {},`
`14`	`14`	`"outputs": [],`
`15`	`15`	`"source": [`
`@@ -18,7 +18,7 @@`
`18`	`18`	`"import matplotlib.pyplot as plt\n",`
`19`	`19`	`"from scipy import stats\n",`
`20`	`20`	`"import numpy as np\n",`
`21`		`- "df = pd.read_csv(\"../Data/german_credit_data.csv\")"`
	`21`	`+ "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/german_credit_data.csv\")"`
`22`	`22`	`]`
`23`	`23`	`},`
`24`	`24`	`{`
Original file line number	Diff line number	Diff line change
`@@ -14,8 +14,8 @@`
`14`	`14`	`"outputs": [],`
`15`	`15`	`"source": [`
`16`	`16`	`"import pandas as pd\n",`
`17`		`- "df1 = pd.read_csv('../Data/mark.csv',header = 0)\n",`
`18`		`- "df2 = pd.read_csv('../Data/student.csv',header = 0)"`
	`17`	`+ "df1 = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/mark.csv',header = 0)\n",`
	`18`	`+ "df2 = pd.read_csv('https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/student.csv',header = 0)"`
`19`	`19`	`]`
`20`	`20`	`},`
`21`	`21`	`{`
Original file line number	Diff line number	Diff line change
`@@ -9,13 +9,13 @@`
`9`	`9`	`},`
`10`	`10`	`{`
`11`	`11`	`"cell_type": "code",`
`12`		`- "execution_count": 34,`
	`12`	`+ "execution_count": 1,`
`13`	`13`	`"metadata": {},`
`14`	`14`	`"outputs": [],`
`15`	`15`	`"source": [`
`16`	`16`	`"import pandas as pd\n",`
`17`	`17`	`"import numpy as np\n",`
`18`		`- "df = pd.read_csv(\"../Data/student.csv\")"`
	`18`	`+ "df = pd.read_csv(\"https://raw.githubusercontent.com/TrainingByPackt/Data-Science-with-Python/master/Chapter01/Data/student.csv\")"`
`19`	`19`	`]`
`20`	`20`	`},`
`21`	`21`	`{`