bitliner · October 4, 2024 14:07 · Oct 4, 2024 · Oct 4, 2024 · Dec 2, 2022 · Dec 2, 2022
diff --git a/pandas.md b/pandas.md
@@ -75,9 +75,11 @@ data = {'Name': ['Tom', 'nick', 'krish', 'jack'],
         'Age': [20, 21, 19, 18]}
 
 df = pd.DataFrame(data)
+```
 
 OR
 
+```python
 data = [
     {"name": "Alice", "age": 25, "city": "New York"},
     {"name": "Bob", "age": 30, "city": "Los Angeles"},

diff --git a/pandas.md b/pandas.md
@@ -75,6 +75,17 @@ data = {'Name': ['Tom', 'nick', 'krish', 'jack'],
         'Age': [20, 21, 19, 18]}
 
 df = pd.DataFrame(data)
+
+OR
+
+data = [
+    {"name": "Alice", "age": 25, "city": "New York"},
+    {"name": "Bob", "age": 30, "city": "Los Angeles"},
+    {"name": "Charlie", "age": 35, "city": "Chicago"}
+]
+
+# Create a DataFrame
+df = pd.DataFrame(data)
 ```
 
 ## filter rows

diff --git a/pandas.md b/pandas.md
@@ -2,11 +2,12 @@
 
 ## merge two dataframe
 
+Append the columns of df2 to df1
+
 ```python
 df1.join(df2)
 ```
 
-There are also way to make sql-join like operation. The one above simply append the columns of df2 to df1
 
 ## select columns
 

diff --git a/pandas.md b/pandas.md
@@ -1,5 +1,13 @@
 # pandas
 
+## merge two dataframe
+
+```python
+df1.join(df2)
+```
+
+There are also way to make sql-join like operation. The one above simply append the columns of df2 to df1
+
 ## select columns
 
 Selecting columns based on their name

diff --git a/pandas.md b/pandas.md
@@ -2,15 +2,15 @@
 
 ## select columns
 
-**Selecting columns based on their name**
+Selecting columns based on their name
 
 ```python
 df['hue'] # single column
 
 df[['alcohol','hue']] # multiple columns
 ```
 
-**Selecting a subset of columns based on difference of columns**
+Selecting a subset of columns based on difference of columns
 
 ```python
 df[df.columns.difference([‘alcohol’,’hue’])]

diff --git a/pandas.md b/pandas.md
@@ -1,5 +1,21 @@
 # pandas
 
+## select columns
+
+**Selecting columns based on their name**
+
+```python
+df['hue'] # single column
+
+df[['alcohol','hue']] # multiple columns
+```
+
+**Selecting a subset of columns based on difference of columns**
+
+```python
+df[df.columns.difference([‘alcohol’,’hue’])]
+```
+
 ## rename column
 
 ```python

diff --git a/pandas.md b/pandas.md
@@ -1,5 +1,11 @@
 # pandas
 
+## rename column
+
+```python
+df.rename(columns = {'old_col1':'new_col1', 'old_col2':'new_col2'}, inplace = True)
+```
+
 ## add column
 
 ```python

diff --git a/pandas.md b/pandas.md
@@ -13,6 +13,12 @@ OR
 df2=df.assign(Discount_Percent=lambda x: x.Fee * x.Discount / 100)
 ```
 
+OR
+
+```python
+ff['Discounted_Price'] = df.apply(lambda row: row.Cost - (row.Cost * 0.1), axis = 1)
+```
+
 ## create data frame
 
 ```python

diff --git a/pandas.md b/pandas.md
@@ -46,6 +46,12 @@ df = pd.DataFrame(data)
 df[df.apply(lambda x: x['b'] > x['c'], axis=1)]
 ```
 
+## process or transform a column
+
+```python
+df['Col4'] = df.apply(lambda row:", ".join([(val if val[0]=='a' else "["+val+"]") for val in row if not pd.isna(val)]), axis=1)
+```
+
 ## test dataframe equality
 
 ```python

diff --git a/pandas.md b/pandas.md
@@ -44,4 +44,13 @@ df = pd.DataFrame(data)
 
 ```python
 df[df.apply(lambda x: x['b'] > x['c'], axis=1)]
+```
+
+## test dataframe equality
+
+```python
+from pandas.testing import assert_frame_equal
+df1 = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
+df2 = pd.DataFrame({'a': [1, 2], 'b': [3.0, 4.0]})
+assert_frame_equal(df1, df1)
 ```
diff --git a/pandas.md b/pandas.md
@@ -33,16 +33,15 @@ df = pd.DataFrame(data, columns=['Name', 'Age'])
 
 OR
 
-```
+```python
 data = {'Name': ['Tom', 'nick', 'krish', 'jack'],
         'Age': [20, 21, 19, 18]}
 
-# Create DataFrame
 df = pd.DataFrame(data)
 ```
 
 ## filter rows
 
-```
+```python
 df[df.apply(lambda x: x['b'] > x['c'], axis=1)]
 ```
diff --git a/pandas.md b/pandas.md
@@ -31,6 +31,16 @@ data = [['tom', 10], ['nick', 15], ['juli', 14]]
 df = pd.DataFrame(data, columns=['Name', 'Age'])
 ```
 
+OR
+
+```
+data = {'Name': ['Tom', 'nick', 'krish', 'jack'],
+        'Age': [20, 21, 19, 18]}
+  
+# Create DataFrame
+df = pd.DataFrame(data)
+```
+
 ## filter rows
 
 ```

diff --git a/pandas.md b/pandas.md
@@ -2,17 +2,35 @@
 
 ## add column
 
-```
+```python
 tutors = ['William', 'Henry', 'Michael', 'John', 'Messi']
 df2 = df.assign(TutorsAssigned=tutors)
 ```
 
 OR
 
-```
+```python
 df2=df.assign(Discount_Percent=lambda x: x.Fee * x.Discount / 100)
 ```
 
+## create data frame
+
+```python
+data = [10,20,30,40,50,60]
+
+# Create the pandas DataFrame with column name is provided explicitly
+df = pd.DataFrame(data, columns=['Numbers'])
+```
+
+OR
+
+```python
+data = [['tom', 10], ['nick', 15], ['juli', 14]]
+
+# Create the pandas DataFrame
+df = pd.DataFrame(data, columns=['Name', 'Age'])
+```
+
 ## filter rows
 
 ```

diff --git a/pandas.md b/pandas.md
@@ -1,6 +1,6 @@
 # pandas
 
-### add column
+## add column
 
 ```
 tutors = ['William', 'Henry', 'Michael', 'John', 'Messi']
@@ -13,7 +13,7 @@ OR
 df2=df.assign(Discount_Percent=lambda x: x.Fee * x.Discount / 100)
 ```
 
-### filter rows
+## filter rows
 
 ```
 df[df.apply(lambda x: x['b'] > x['c'], axis=1)]

diff --git a/pandas.md b/pandas.md
@@ -1,6 +1,6 @@
 # pandas
 
-## add column
+### add column
 
 ```
 tutors = ['William', 'Henry', 'Michael', 'John', 'Messi']
@@ -11,4 +11,10 @@ OR
 
 ```
 df2=df.assign(Discount_Percent=lambda x: x.Fee * x.Discount / 100)
+```
+
+### filter rows
+
+```
+df[df.apply(lambda x: x['b'] > x['c'], axis=1)]
 ```
diff --git a/pandas.md b/pandas.md
@@ -7,6 +7,8 @@ tutors = ['William', 'Henry', 'Michael', 'John', 'Messi']
 df2 = df.assign(TutorsAssigned=tutors)
 ```
 
+OR
+
 ```
 df2=df.assign(Discount_Percent=lambda x: x.Fee * x.Discount / 100)
 ```
diff --git a/pandas.md b/pandas.md
@@ -0,0 +1,12 @@
+# pandas
+
+## add column
+
+```
+tutors = ['William', 'Henry', 'Michael', 'John', 'Messi']
+df2 = df.assign(TutorsAssigned=tutors)
+```
+
+```
+df2=df.assign(Discount_Percent=lambda x: x.Fee * x.Discount / 100)
+```