Data Cleaning
The data which is obtained from the primary sources is termed the raw data and required a lot of preprocessing before we can derive any conclusions from it or do some modeling on it. Those preprocessing steps are known as data cleaning and it includes, outliers removal, null value imputation, and removing discrepancies of any sort in the data inputs.
Python3
df.isnull(). sum () |
Output:
So there is one null value in the ‘winddirection’ as well as the ‘windspeed’ column. But what’s up with the column name wind direction?
Python3
df.columns |
Output:
Index(['day', 'pressure ', 'maxtemp', 'temperature', 'mintemp', 'dewpoint', 'humidity ', 'cloud ', 'rainfall', 'sunshine', ' winddirection', 'windspeed'], dtype='object')
Here we can observe that there are unnecessary spaces in the names of the columns let’s remove that.
Python3
df.rename( str .strip, axis = 'columns' , inplace = True ) df.columns |
Output:
Index(['day', 'pressure', 'maxtemp', 'temperature', 'mintemp', 'dewpoint', 'humidity', 'cloud', 'rainfall', 'sunshine', 'winddirection', 'windspeed'], dtype='object')
Now it’s time for null value imputation.
Python3
for col in df.columns: # Checking if the column contains # any null values if df[col].isnull(). sum () > 0 : val = df[col].mean() df[col] = df[col].fillna(val) df.isnull(). sum (). sum () |
Output:
0
Rainfall Prediction using Machine Learning – Python
Today there are no certain methods by using which we can predict whether there will be rainfall today or not. Even the meteorological department’s prediction fails sometimes. In this article, we will learn how to build a machine-learning model which can predict whether there will be rainfall today or not based on some atmospheric factors. This problem is related to Rainfall Prediction using Machine Learning because machine learning models tend to perform better on the previously known task which needed highly skilled individuals to do so.