Upload 3 files

requirements.txt

@@ -0,0 +1,60 @@
+altair==4.2.2
+attrs==23.1.0
+blinker==1.6.2
+cachetools==5.3.0
+certifi==2022.12.7
+charset-normalizer==3.1.0
+click==8.1.3
+colorama==0.4.6
+contourpy==1.0.7
+cycler==0.11.0
+decorator==5.1.1
+entrypoints==0.4
+fonttools==4.39.3
+gitdb==4.0.10
+GitPython==3.1.31
+idna==3.4
+importlib-metadata==6.6.0
+Jinja2==3.1.2
+joblib==1.2.0
+jsonschema==4.17.3
+kiwisolver==1.4.4
+markdown-it-py==2.2.0
+MarkupSafe==2.1.2
+matplotlib==3.7.1
+mdurl==0.1.2
+nltk==3.8.1
+numpy==1.24.3
+packaging==23.1
+pandas==2.0.1
+Pillow==9.5.0
+protobuf==3.20.3
+pyarrow==11.0.0
+pydeck==0.8.1b0
+Pygments==2.15.1
+Pympler==1.0.1
+pyparsing==3.0.9
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+regex==2023.3.23
+requests==2.29.0
+rich==13.3.5
+six==1.16.0
+smmap==5.0.0
+streamlit==1.22.0
+tenacity==8.2.2
+textblob==0.17.1
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.1
+tqdm==4.65.0
+typing_extensions==4.5.0
+tzdata==2023.3
+tzlocal==4.3
+urllib3==1.26.15
+validators==0.20.0
+watchdog==3.0.0
+wordcloud==1.9.1.1
+zipp==3.15.0

smart.farming.sentiment.py

@@ -0,0 +1,142 @@
+import pandas as pd
+import streamlit as st
+from textblob import TextBlob
+import re
+import matplotlib.pyplot as plt
+
+import nltk
+from nltk.corpus import stopwords
+from collections import Counter
+from wordcloud import WordCloud
+nltk.download('stopwords')
+
+st.set_page_config(
+    page_title="Smart Farming Sentiment Analysis",
+    page_icon="🌱",
+    layout="wide"
+    )
+
+def set_cleantext(dataframe):
+    #Sentence less than 10 words
+    dataframe = dataframe[dataframe['sentences'].apply(lambda x: len(x.split()) >= 10)]
+    #Delete web address
+    dataframe.loc[:, 'sentences'] = dataframe['sentences'].str.replace(url_pattern, '', regex=True)   
+    #Removing empty spaces
+    dataframe.loc[:, 'sentences'] = dataframe['sentences'].str.replace('\n', ' ')
+    dataframe.loc[:, 'sentences'] = dataframe['sentences'].str.strip()
+
+    #Delete duplicate sentences
+    dataframe = dataframe.drop_duplicates(subset=['sentences'])
+    dataframe.reset_index(drop=True, inplace=True)
+
+    return dataframe
+
+def set_textblob(dataframe):
+    # apply TextBlob to the value in the column
+    text_blob = TextBlob(dataframe['sentences'])
+    # add new columns for polarity and subjectivity
+    dataframe['polarity'] = text_blob.sentiment.polarity
+    dataframe['subjectivity'] = text_blob.sentiment.subjectivity
+    return dataframe
+
+def delete_stopwords(dataframe):
+    #Delete stopwords
+    stop = stopwords.words('english')
+    dataframe['sentences'] = dataframe['sentences'].apply(lambda x: ' '.join([word for word in x.split() if word not in (stop)]))
+    return dataframe
+
+df = pd.read_csv("smartfarmingsentences.csv")
+num_ori = df.shape[0]
+
+st.title("Smart Farming Sentiment Analysis")
+st.subheader("Sentiment Analysis of Smart Farming Knowledge Graph")
+
+url_pattern = re.compile(r'https?://\S+')
+df = set_cleantext(df)
+
+num_clean = df.shape[0]
+
+kolom_num1, kolom_num2, kolom_num3 = st.columns(3)
+
+with kolom_num1:
+    st.text("Original Sentences: " + str(num_ori))
+with kolom_num2:
+    st.text("Sentences Count: " + str(num_clean))
+with kolom_num3:
+    st.text("Deleted Sentences: " + str(num_ori - num_clean))
+
+#Sentiment Analysis
+df = df.apply(set_textblob, axis=1)
+st.dataframe(df, use_container_width=True)
+
+#Separate polarity by Positive, Neutral, Negative
+df_pos = df[df['polarity'] > 0]
+df_neu = df[df['polarity'] == 0]
+df_neg = df[df['polarity'] < 0]
+
+#Separate subjectivity by Objective, Subjective
+df_obj = df[df['subjectivity'] <= 0.3]
+df_sub = df[df['subjectivity'] > 0.3]
+
+figp, ax = plt.subplots()
+bars = ax.bar(['Positive', 'Neutral', 'Negative'], [len(df_pos), len(df_neu), len(df_neg)], color=['green', 'gray', 'red'])
+ax.set_xlabel('Sentiment')
+ax.set_ylabel('Count')
+ax.set_title('Sentiment Analysis')
+
+figs, ax = plt.subplots()
+bars = ax.bar(['Objective', 'Subjective'], [len(df_obj), len(df_sub)], color=['green', 'red'])
+ax.set_xlabel('Subjectivity')
+ax.set_ylabel('Count')
+ax.set_title('Subjectivity Analysis')
+
+kolom_polar, kolom_subject = st.columns(2)
+
+with kolom_polar:
+    #Show Sentiment Analysis
+    st.subheader("Sentiment Analysis")
+    st.text("Positive: " + str(df_pos.shape[0]))
+    st.text("Neutral: " + str(df_neu.shape[0]))
+    st.text("Negative: " + str(df_neg.shape[0]))
+    # Create a bar chart
+    st.pyplot(figp)
+with kolom_subject:
+    #Show Subjectivity Analysis
+    st.subheader("Subjectivity Analysis")
+    st.text("Objective: " + str(df_obj.shape[0]))
+    st.text("Subjective: " + str(df_sub.shape[0]))
+    st.text("---")
+    # Create a bar chart
+    st.pyplot(figs)
+
+#Make Lowercase
+df['sentences'] = df['sentences'].str.lower()
+
+#remove punctuation . , ! ? : ; " ' ( ) [ ] { } < > / \ | ` ~ @ # $ % ^ & * - _ = +
+df['sentences'] = df['sentences'].str.replace('[.,!?;:"\'()\[\]{}<>\\/|`~@#$%^&*\-_+=]', '')
+
+#Stopwords
+df = delete_stopwords(df)
+
+#Delete one or two words
+df['sentences'] = df['sentences'].apply(lambda x: ' '.join([word for word in x.split() if len(word) > 2]))
+
+#Remove custom words
+custom_words = ["s", "al", 'view', 'article', 'google', 'scholar', "scopus", "crossref"]
+df['sentences'] = df['sentences'].apply(lambda x: ' '.join([word for word in x.split() if word not in (custom_words)]))
+
+#Make Wordcloud
+all_words = ' '.join([text for text in df['sentences']])
+wordcloud = WordCloud(width=1024, height=1024, random_state=21, max_font_size=110).generate(all_words)
+st.subheader("Wordcloud")
+st.text("Total Words: " + str(len(all_words)))
+plt.figure(figsize=(10, 7))
+plt.imshow(wordcloud, interpolation="bilinear")
+plt.axis('off')
+st.pyplot(plt)
+
+#Show Top 10 Words
+word_freq = Counter(all_words.split()).most_common(1000)
+df_word_freq = pd.DataFrame(word_freq, columns=['Word', 'Frequency'])
+st.subheader("Top 10 Words")
+st.dataframe(df_word_freq.head(1000), use_container_width=True)