Tips and Tricks for pandas operation

pandas_trick.py

# to read data
df_data=pd.read_csv("csvfile.csv")

#replace value in columns
df_data = df_data.replace({
    'colname': {
        'value': 'new_value'
    }
})

# drop columns
df_data.drop(['colname'], inplace=True, axis = 1)

# remove list of rows of certain values
df_data = df_data[~df_data['column'].isin( ['values'] )]

# to see count of each values in columns
df_data.colname.value_counts()

# to see summary
df_data.head(5)

#to see shape
df_data.shape

#to see values of columns
list(df_data['colname'].values)

# table transformation to (row_id A 1.0 )
df_data = pd.melt(df_data, id_vars='key_id', var_name='colname', value_name='value').sort_values('key_id').reset_index(drop=True)

#filling na
df_data['colname'] = df_data['colname'].fillna(value = 'value')

#-------------------------------------- GRAPH ----------------------------------------------------------------#
# https://www.shanelynn.ie/bar-plots-in-python-using-pandas-dataframes/


# draw bar and write value
        ax=df_data_train.diagnosis.value_counts().plot.bar(align='edge')

        for rect in ax.patches:
            y_value=rect.get_height()

            x_value = rect.get_x() + rect.get_width() / 2
            # Number of points between bar and label. Change to your liking.
            space = 10
            # Vertical alignment for positive values
            va = 'bottom'
            #ha='left'

            # If value of bar is negative: Place label below bar
            if x_value < 0:
                # Invert space to place label below
                space *= -1
                # Vertically align label at top
                va = 'top'
                #ha='right'

            # Use Y value as label and format number with one decimal place
            label = "{}".format(int(y_value))

            ax.annotate(
                    label,                      # Use `label` as label
                    (x_value, y_value),         # Place label at end of the bar
                    xytext=(0, space),          # Vertically shift label by `space`
                    textcoords="offset points", # Interpret `xytext` as offset in points
                    ha='center',                # Horizontally center label
                    va=va)                      # Vertically align label differently for
                                                # positive and negative values.


        # plt.show()