code

!pip install pandas
import pandas as pd
print(pd.__version__)
!pip install nltk
import nltk
print(nltk.__version__)
from nltk.sentiment.vader import SentimentIntensityAnalyzer
import re
from textblob import TextBlob
from wordcloud import WordCloud
import seaborn as sns
import matplotlib.pyplot as plt
import cufflinks as cf
%matplotlib inline
from plotly.offline import init_notebook_mode,iplot
init_notebook_mode(connected = True)
cf.go_offline();
import plotly.graph_objs as go
from plotly.subplots import make_subplots

import warnings
warnings.filterwarnings("ignore")
warnings.warn("this will not show")
pd.set_option('display.max_columns',None)
df= pd.read_csv("/content/cleaned_dataset.csv")
del df[df.columns[0]]
import pandas as pd

# Load your dataset
df = pd.read_csv("/content/cleaned_dataset.csv")
columns_to_clean=['reviewerName','overall','reviewText','reviewTime','day_diff','helpful_yes','helpful_no','total_vote','score_pos_neg_diff','score_average_rating','wilson_lower_bound']
df_cleaned=df.dropna(subset=columns_to_clean)
df_cleaned.to_csv('cleaned_dataset.csv',index=False)

# Check for missing values
df = pd.read_csv("/content/cleaned_dataset.csv")
missing_values = df.isnull().sum().sum()
if missing_values == 0:
    print("No missing values found.")
else:
    print("Missing values found in the dataset.total:{missing_values}")

# Check for duplicates
duplicate_rows = df.duplicated().sum()
if duplicate_rows == 0:
    print("No duplicate rows found.")
else:
    print("Duplicate rows found.")

# Validate data types
print("Data types:")
print(df.dtypes)

# Explore outliers (This example assumes numerical columns)
outliers = df.describe().loc[['min', 'max']].T
print("Outliers (min/max values per column):")
print(outliers)
df = pd.read_csv("/content/cleaned_dataset.csv")
def missing_values_analysis(df):
  na_columns_=[col for col in df.columns if df[col].isnull().sum()>0]
  n_miss = pd.Series(df[na_columns_].isnull().sum())
  ratio_ = (df[na_columns_].isnull().sum()/df.shape[0]*100).sort_values(ascending=True)
  missing_df = pd.concat([n_miss,np.round(ratio_,2)],axis=1,keys=['Missing Values','Ratio'])
  return missing_df
def check_dataframe(df, head=5, tail=5):
    print("SHAPE".center(82, '~'))
    print('Rows: {}'.format(df.shape[0]))
    print('Columns: {}'.format(df.shape[1]))
    print("TYPES".center(82, '~'))
    print(df.dtypes)
    print("".center(82, '~'))
    print(missing_values_analysis(df))
    print('DUPLICATED VALUES'.center(83, '~'))
    print(df.duplicated().sum())
    print("QUANTILES".center(82, '~'))
    numerical_columns=df.select_dtypes(include=['int','float'])
    quantiles=numerical_columns.quantile([0,0.05,0.50,0.95,0.99,1])
    print("QUANTILES:")
    print(quantiles)
check_dataframe(df)
def check_class(data_frame):
  nunique_df=pd.DataFrame({'Variable':data_frame.columns,
                           'Classes':[data_frame[i].nunique()\
                                      for i in data_frame.columns]})
  nunique_df=nunique_df.sort_values('Classes',ascending=False)
  nunique_df=nunique_df.reset_index(drop=True)
  return nunique_df
check_class(df)

import plotly.graph_objects as go
from plotly.subplots import make_subplots
constraints=['#B34D22','#EBE00C','#1FEB0C','#0C92EB','#EB0CD5']
def categeorical_variable_summary(df,column_name):
  fig=make_subplots(rows=1,cols=2,
                    subplot_titles=('Countplot','Percentage'),
                    specs=[[{"type":"xy"},{'type': "domain"}]]) # Define domain here
  fig.add_trace(go.Bar(y=df[column_name].value_counts().values.tolist(),
                       x=[str(i)for i in df[column_name].value_counts().index],
                       text=df[column_name].value_counts().values.tolist(),
                       textfont=dict(size=14),
                       name=column_name,
                       textposition='auto',
                      showlegend=False,
                       marker=dict(color=constraints,
                                   line=dict(color='#DBE6EC',
                                             width=1))),
                              row=1,col=1)
  fig.add_trace(go.Pie(labels=df[column_name].value_counts().keys(),
                       values=df[column_name].value_counts().values,
                       textfont=dict(size=18),
                       textposition='auto',
                       showlegend=False,
                       name=column_name,
                       marker=dict(colors=constraints)),
                row=1,col=2)
  fig.update_layout(title={'text':column_name,
                           'y':0.9,
                           'x':0.5,
                           'xanchor':'center',
                           'yanchor':'top'},
                    template='plotly_white')
  display(fig)

categeorical_variable_summary(df,'overall')