Deleted Personality_prediction/.idea/inspectionProfiles/profiles_settings.xml,...

Deleted Personality_prediction/.idea/inspectionProfiles/profiles_settings.xml, Personality_prediction/.idea/.gitignore, Personality_prediction/.idea/Personality_prediction.iml, Personality_prediction/.idea/misc.xml, Personality_prediction/.idea/modules.xml, Personality_prediction/Personality_prediction/.idea/inspectionProfiles/profiles_settings.xml, Personality_prediction/sample_predictor.py, Personality_prediction/separate_clean_and_unclean.py, Personality_prediction/simple_rnn.py files

Personality_prediction/.idea/.gitignore

-# Default ignored files
-/shelf/
-/workspace.xml
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml
-# Editor-based HTTP Client requests
-/httpRequests/

Personality_prediction/.idea/Personality_prediction.iml

-<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="Python 3.8 (2)" jdkType="Python SDK" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-</module>
\ No newline at end of file

Personality_prediction/.idea/inspectionProfiles/profiles_settings.xml

-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>
\ No newline at end of file

Personality_prediction/.idea/misc.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (2)" project-jdk-type="Python SDK" />
-</project>
\ No newline at end of file

Personality_prediction/.idea/modules.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectModuleManager">
-    <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/Personality_prediction.iml" filepath="$PROJECT_DIR$/.idea/Personality_prediction.iml" />
-    </modules>
-  </component>
-</project>
\ No newline at end of file

Personality_prediction/Personality_prediction/.idea/inspectionProfiles/profiles_settings.xml

-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>
\ No newline at end of file

Personality_prediction/sample_predictor.py

-import csv
-import os
-import pickle
-
-import numpy as np
-from keras.models import load_model
-from keras.preprocessing import sequence
-from nltk.corpus import stopwords
-from nltk.stem import WordNetLemmatizer
-
-MODELS_DIRECTORY = "models"
-DATA_DIRECTORY = "data/sample_data"
-SAMPLE_TWEETS_PATH = os.path.join(DATA_DIRECTORY, "0xnickrodriguez_tweets.csv")
-
-DIMENSIONS = ["IE", "NS", "FT", "PJ"]
-DIMENSIONS_with_strings = ["Introversion Extroversion", "Intuition Sensing", "Feeling Thinking", "Perceiving Judging"]
-MODEL_BATCH_SIZE = 128
-TOP_WORDS = 2500
-MAX_POST_LENGTH = 40
-EMBEDDING_VECTOR_LENGTH = 20
-
-final = ""
-
-x_test = []
-with open(SAMPLE_TWEETS_PATH, "r", encoding="ISO-8859-1") as f:
-    reader = csv.reader(f)
-    for row in f:
-        x_test.append(row)
-
-types = [
-    "INFJ",
-    "ENTP",
-    "INTP",
-    "INTJ",
-    "ENTJ",
-    "ENFJ",
-    "INFP",
-    "ENFP",
-    "ISFP",
-    "ISTP",
-    "ISFJ",
-    "ISTJ",
-    "ESTP",
-    "ESFP",
-    "ESTJ",
-    "ESFJ",
-]
-types = [x.lower() for x in types]
-lemmatizer = WordNetLemmatizer()
-stop_words = stopwords.words("english")
-
-
-def lemmatize(x):
-    lemmatized = []
-    for post in x:
-        temp = post.lower()
-        for type_ in types:
-            temp = temp.replace(" " + type_, "")
-        temp = " ".join(
-            [
-                lemmatizer.lemmatize(word)
-                for word in temp.split(" ")
-                if (word not in stop_words)
-            ]
-        )
-        lemmatized.append(temp)
-    return np.array(lemmatized)
-
-
-for k in range(len(DIMENSIONS)):
-    model = load_model(
-        os.path.join(MODELS_DIRECTORY, "rnn_model_{}.h5".format(DIMENSIONS[k]))
-    )
-    tokenizer = None
-    with open(
-            os.path.join(MODELS_DIRECTORY, "rnn_tokenizer_{}.pkl".format(DIMENSIONS[k])), "rb"
-    ) as f:
-        tokenizer = pickle.load(f)
-
-
-    def preprocess(x):
-        lemmatized = lemmatize(x)
-        tokenized = tokenizer.texts_to_sequences(lemmatized)
-        return sequence.pad_sequences(tokenized, maxlen=MAX_POST_LENGTH)
-
-
-    predictions = model.predict(preprocess(x_test))
-    prediction = float(sum(predictions) / len(predictions))
-    print(DIMENSIONS_with_strings[k])
-    print(prediction)
-    if prediction >= 0.5:
-        final += DIMENSIONS[k][1]
-        print("Personality type - ", DIMENSIONS[k][1])
-
-    else:
-        final += DIMENSIONS[k][0]
-        print("Personality type - ", DIMENSIONS[k][0])
-
-    print("")
-
-print("")
-print("Personality Type of the Person : {}  ".format(final))

Personality_prediction/separate_clean_and_unclean.py

-import os
-import collections
-import pandas as pd
-import csv
-
-
-DATA_DIRECTORY = "data"
-MBTI_RAW_CSV_PATH = os.path.join(DATA_DIRECTORY, "mbti_personality.csv")
-MBTI_CLEAN_CSV_PATH = os.path.join(DATA_DIRECTORY, "mbti_personality_clean.csv")
-MBTI_UNCLEAN_CSV_PATH = os.path.join(DATA_DIRECTORY, "mbti_personality_unclean.csv")
-MBTI_TO_FREQUENCY_DICT = {
-    "ISTJ": 0.11,
-    "ISFJ": 0.09,
-    "INFJ": 0.04,
-    "INTJ": 0.05,
-    "ISTP": 0.05,
-    "ISFP": 0.05,
-    "INFP": 0.06,
-    "INTP": 0.06,
-    "ESTP": 0.04,
-    "ESFP": 0.04,
-    "ENFP": 0.08,
-    "ENTP": 0.06,
-    "ESTJ": 0.08,
-    "ESFJ": 0.09,
-    "ENFJ": 0.05,
-    "ENTJ": 0.05,
-}
-
-
-df = pd.read_csv(MBTI_RAW_CSV_PATH)
-
-counts = collections.defaultdict(int)
-for mbti in df["type"]:
-    counts[mbti] += 1
-
-limiting_type = None
-min_size = float("infinity")
-for mbti in counts.keys():
-    size = counts[mbti] / MBTI_TO_FREQUENCY_DICT[mbti]
-    if size < min_size:
-        min_size = size
-        limiting_type = mbti
-
-dic = collections.defaultdict(list)
-for index, row in df.iterrows():
-    dic[row["type"]].append(row)
-
-unclean_list = []
-with open(MBTI_CLEAN_CSV_PATH, "w", encoding="utf-8") as f:
-    writer = csv.writer(f)
-    writer.writerow(["type", "posts"])
-
-    for mbti in MBTI_TO_FREQUENCY_DICT.keys():
-        list1 = dic[mbti]
-        for x in range(0, int(round(min_size * MBTI_TO_FREQUENCY_DICT[mbti]))):
-            writer.writerow(list1[x])
-        unclean_list.append(
-            list1[int(round(min_size * MBTI_TO_FREQUENCY_DICT[mbti])) : len(list1)]
-        )
-
-with open(MBTI_UNCLEAN_CSV_PATH, "w", encoding="utf-8") as f:
-    writer = csv.writer(f)
-    writer.writerow(["type", "posts"])
-    for mbti in unclean_list:
-        for x in mbti:
-            writer.writerow(x)